git-disl/awesome-LLM-game-agent-papers

A Survey on Large Language Model-Based Game Agents (ACM CSUR)

965

169 commits

updated Jun 7, 2026

arxiv.org/pdf/2404.02039.pdf

See the code

README

A Survey on Large Language Model-Based Game Agents (ACM CSUR)

Stars Forks

🔥 Must-read papers for LLM-based Game agents.

📘 Our survey has been accepted by ACM Computing Surveys (CSUR). We are preparing the camera ready. Feel free to reach out if you find missing reference.

💫 We continuously update the GitHub list on a weekly basis.

📝 If you discover any papers that are suitable but not yet included, please open an issue or submit a pull request.

Browse by Mechanism

#planning (145)
#memory (44)
#multi-agent (78)
#world-model (18)
#tool-use (20)
#training (160)
#self-improvement (34)
#prompting (28)
#role-play (9)
#vlm (37)
#generation (11)

By Genre

minecraft

[2026/05] GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents arXiv [paper] #minecraft #training #vlm
[2026/05] Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM Agents arXiv [paper] #minecraft #self-improvement
[2026/04] Experience Transfer for Multimodal LLM Agents in Minecraft Game arXiv [paper] #minecraft
[2026/04] Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game arXiv [paper] #minecraft #memory #multi-agent #vlm
[2026/03] BLOCK: An Open-Source Bi-Stage MLLM Character-to-Skin Pipeline for Minecraft arXiv [paper] #minecraft #vlm
[2026/02] Requesting Expert Reasoning: Augmenting LLM Agents with Learned Collaborative Intervention arXiv [paper] #minecraft
[2026/01] MineNPC-Task: Task Suite for Memory-Aware Minecraft Agents arXiv [paper] #minecraft
[2025/12] Synergizing Code Coverage and Gameplay Intent: Coverage-Aware Game Playtesting with LLM-Guided Reinforcement Learning arXiv [paper] #minecraft #training
[2025/11] Knowledge Graph-enhanced Large Language Model for Incremental Game PlayTesting IEICE Transactions on Information and Systems 2025 [paper] #minecraft #memory
[2025/09] PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments 2025 IEEE Conference on Games (CoG) 2025 [paper] #minecraft #multi-agent #self-improvement
[2025/09] Experience-based Knowledge Correction for Robust Planning in Minecraft ICLR 2026 Poster [paper] #minecraft #planning
[2025/08] CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks Findings of EMNLP 2025 [paper] #minecraft #planning #multi-agent
[2025/08] Vistawise: Building Cost-effective Agent with Cross-modal Knowledge Graph for Minecraft EMNLP 2025 [paper] #minecraft #memory #tool-use
[2025/07] VoyagerVision: Investigating the Role of Multi-modal Information for Open-ended Learning Systems arXiv [paper] #minecraft #vlm
[2025/07] Referential ambiguity and clarification requests: comparing human and LLM behaviour Proceedings of the Eighth Workshop on Computational Models of Reference, Anaphora and Coreference 2025 [paper] #minecraft
[2025/06] Optimus-3: Towards Generalist Multimodal Minecraft Agents with Scalable Task Experts arXiv [paper][code] #minecraft #planning
[2025/06] Matrix-Game: Interactive World Foundation Model arXiv [paper][code] #minecraft
[2025/06] GuessBench: Sensemaking Multimodal Creativity in the Wild arXiv [paper] #minecraft #training #vlm
[2025/05] Don’t Just Follow MLLM Plans: Robust and Efficient Planning for Open-World Agents arXiv [paper] #minecraft #planning #vlm
[2025/05] Knowledge Retrieval in LLM Gaming: A Shift from Entity-Centric to Goal-Oriented Graphs Knowledge-Based Systems 2025 [paper] #minecraft #planning #memory
[2025/05] BeliefNest: A Joint Action Simulator for Embodied Agents with Theory of Mind arXiv [paper] #minecraft
[2025/05] MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning NeurIPS 2025 poster [paper] #minecraft #training
[2025/05] WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents NeurIPS 2025 poster [paper] #minecraft #planning #world-model #prompting
[2025/04] Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning arXiv [paper][code] #minecraft #multi-agent #training
[2025/04] WALL-E 2.0: World Alignment by NeuroSymbolic Learning Improves World Model-based LLM Agents arXiv [paper][code] #minecraft #planning #world-model #prompting
[2025/03] Uncertainty in Action: Confidence Elicitation in Embodied Agents arXiv [paper] #minecraft
[2025/03] Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems arXiv [paper] #minecraft #planning #multi-agent #tool-use
[2025/03] NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains ICLR 2025 Poster [paper] #minecraft
[2025/03] Word2Minecraft: Generating 3D Game Levels through Large Language Models arXiv [paper][code] #minecraft #generation
[2025/03] Plancraft: an evaluation dataset for planning with LLM agents COLM 2025 [paper] #minecraft #planning #memory #tool-use
[2025/02] GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks arXiv [paper][code] #minecraft
[2025/02] Optimus-2: Multimodal World Model for Open-World Minecraft Agents CVPR 2025 [paper][code] #minecraft #planning #world-model #vlm
[2025/01] LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence ICML 2025 poster [paper] #minecraft #training
[2024/12] TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft arXiv [paper][code] #minecraft #multi-agent #training #vlm
[2024/11] MrSteve: Instruction-Following Agents with What-Where-When Memory ICLR 2025 [paper][code] #minecraft #memory
[2024/10] WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents arXiv [paper][code] #minecraft #planning #world-model
[2024/10] ADAM: An Embodied Causal Agent in Open-World Environments ICLR 2025 [paper][code] #minecraft #planning
[2024/09] MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory ICLR 2025 Poster [paper] #minecraft #memory
[2024/08] Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-horizon Tasks NeurIPS 2024 [paper][code] #minecraft #planning #memory #prompting
[2024/07] Odyssey: Empowering Agents with Open-World Skills. IJCAI 2024 [paper][code] #minecraft #planning #tool-use
[2024/07] OmniJARVIS: Omni-Modal Open-World Agents in Minecraft NeurIPS 2024 [paper][code] #minecraft #training #vlm
[2024/06] VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft Findings of ACL 2024 [paper][code] #minecraft #planning #multi-agent
[2024/03] MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control arXiv [paper][code] #minecraft
[2024/03] MineLand: Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs arXiv [paper][code] #minecraft #multi-agent #vlm
[2024/03] Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation (HAS) ICLR 2024 Workshop [paper] #minecraft #planning #multi-agent #vlm
[2024/02] RL-GPT: Integrating Reinforcement Learning and Code-as-policy NeurIPS 2024 oral [paper] #minecraft #planning #tool-use #training
[2024/01] ReGAL: Refactoring Programs to Discover Generalizable Abstractions ICML 2024 [paper][code] #minecraft
[2023/12] MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception CVPR 2024 [paper][code] #minecraft #planning #vlm
[2023/12] Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft CVPR 2023 [paper] #minecraft #training
[2023/12] Creative Agents: Empowering Agents with Imagination for Creative Tasks UAI 2023 [paper][code] #minecraft #planning
[2023/11] JARVIS-1: Open-world Multi-task Agents with Memory-Augmented Multimodal Language Models TPAMI 2023 [paper][code] #minecraft #planning #memory
[2023/11] See and Think: Embodied Agent in Virtual Environment ECCV 2023 [paper][code] #minecraft #memory
[2023/10] LLaMA Rider: Spurring Large Language Models to Explore the Open World NAACL 2023 [paper][code] #minecraft #planning #training
[2023/10] MCU: A Task-centric Framework for Open-ended Agent Evaluation in Minecraft ICML 2023 [paper][code] #minecraft
[2023/10] Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds ICLR 2024 [paper] #minecraft #vlm
[2023/05] Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory arXiv [paper] #minecraft #training
[2023/05] VOYAGER: An Open-Ended Embodied Agent with Large Language Models FMDM@NeurIPS2023 [paper][code] #minecraft #tool-use #training
[2023/03] Plan4MC: Skill Reinforcement Learning and Planning for Open-World Minecraft Tasks FMDM@NeurIPS2023 [paper][code] #minecraft #planning #training
[2023/02] Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents NeurIPS 2023 [paper][code] #minecraft #planning #prompting
[2022/07] Craft an Iron Sword: Dynamically Generating Interactive Game Characters by Prompting Large Language Models Tuned on Code Wordplay@ACL 2022 [paper] #minecraft

text-adventure

[2026/06] SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training arXiv [paper][code] #text-adventure #memory #training
[2026/06] SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale arXiv [paper] #text-adventure #memory #self-improvement
[2026/06] LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents arXiv [paper] #text-adventure
[2026/06] From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents arXiv [paper] #text-adventure #planning
[2026/06] Cross-Environment Neural Reranking for Sample-Efficient Action Selection in Text-Based Agents arXiv [paper] #text-adventure #training
[2026/06] Unified Context Evolution for LLM Agents arXiv [paper] #text-adventure
[2026/06] When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training arXiv [paper] #text-adventure #training
[2026/05] T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning arXiv [paper][code] #text-adventure #training
[2026/05] PRISM: Perception Reasoning Interleaved for Sequential Decision Making arXiv [paper] #text-adventure #vlm
[2026/05] From History to State: Constant-Context Skill Learning for LLM Agents arXiv [paper] #text-adventure #planning #training
[2026/05] StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction arXiv [paper] #text-adventure #training
[2026/05] AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning arXiv [paper] #text-adventure #training
[2026/05] Belief Memory: Agent Memory Under Partial Observability arXiv [paper] #text-adventure #memory
[2026/05] SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents arXiv [paper] #text-adventure
[2026/05] Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents arXiv [paper] #text-adventure #training #self-improvement
[2026/05] Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning arXiv [paper] #text-adventure #tool-use #training
[2026/05] SkillMaster: Toward Autonomous Skill Mastery in LLM Agents arXiv [paper] #text-adventure #training
[2026/05] PriorZero: Bridging Language Priors and World Models for Decision Making arXiv [paper][code] #text-adventure #planning #world-model #training
[2026/05] Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents arXiv [paper] #text-adventure #memory #tool-use
[2026/05] What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents arXiv [paper] #text-adventure #training
[2026/05] APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents arXiv [paper] #text-adventure #planning #self-improvement
[2026/05] SKILLC: Learning Autonomous Skill Internalization in LLM Agents via Contrastive Credit Assignment arXiv [paper] #text-adventure #training
[2026/05] SkillsInjector: Dynamic Skill Context Construction for LLM Agents arXiv [paper] #text-adventure
[2026/05] SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs arXiv [paper] #text-adventure #memory #tool-use #training
[2026/05] Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning arXiv [paper] #text-adventure #training
[2026/05] Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents arXiv [paper] #text-adventure #memory
[2026/05] PatchBoard: Schema-Grounded State Mutation for Reliable and Auditable LLM Multi-Agent Collaboration arXiv [paper] #text-adventure #multi-agent
[2026/05] Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL arXiv [paper][code] #text-adventure #training
[2026/05] R2V Agent: Teaching SLMs When to Ask for Help arXiv [paper] #text-adventure #training
[2026/05] SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems arXiv [paper] #text-adventure #planning #memory #tool-use
[2026/04] Aligning Progress and Feasibility: A Neuro-Symbolic Dual Memory Framework for Long-Horizon LLM Agents arXiv [paper] #text-adventure #planning #memory
[2026/04] Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents arXiv [paper][code] #text-adventure #training
[2026/04] DORA Explorer: Improving the Exploration Ability of LLMs Without Training arXiv [paper] #text-adventure #planning #prompting
[2026/04] From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents arXiv [paper] #text-adventure #planning
[2026/04] Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows arXiv [paper] #text-adventure #planning #memory #multi-agent
[2026/04] ReDAct: Uncertainty-Aware Deferral for LLM Agents arXiv [paper] #text-adventure
[2026/04] GraSP: Graph-Structured Skill Compositions for LLM Agents arXiv [paper] #text-adventure #planning #memory #self-improvement
[2026/04] DPEPO: Diverse Parallel Exploration Policy Optimization for LLM-based Agents arXiv [paper][code] #text-adventure #training
[2026/03] Hindsight Credit Assignment for Long-Horizon LLM Agents arXiv [paper] #text-adventure #training
[2026/03] How Clued up are LLMs? Evaluating Multi-Step Deductive Reasoning in a Text-Based Game Environment arXiv [paper] #text-adventure #multi-agent #training
[2026/03] RPMS: Enhancing LLM-Based Embodied Planning through Rule-Augmented Memory Synergy arXiv [paper] #text-adventure #planning #memory
[2026/03] RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback arXiv [paper] #text-adventure #memory #training #self-improvement
[2026/03] Reward Prediction with Factorized World States arXiv [paper] #text-adventure #planning #prompting
[2026/02] MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents arXiv [paper] #text-adventure #self-improvement
[2026/02] Active Epistemic Control for Query-Efficient Verified Planning arXiv [paper] #text-adventure #planning
[2026/02] Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents arXiv [paper] #text-adventure #planning #training
[2026/02] TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agents arXiv [paper] #text-adventure #planning
[2026/02] CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent Pipelines arXiv [paper] #text-adventure #planning #world-model #training
[2026/02] Reinforcement World Model Learning for LLM-based Agents arXiv [paper] #text-adventure #world-model
[2026/02] SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards arXiv [paper] #text-adventure #training
[2026/02] SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning arXiv [paper][code] #text-adventure #memory #tool-use #training
[2026/01] Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory arXiv [paper] #text-adventure
[2026/01] Beyond Entangled Planning: Task-Decoupled Planning for Long-Horizon Agents arXiv [paper] #text-adventure #planning #prompting
[2026/01] Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents arXiv [paper] #text-adventure #planning #training
[2026/01] Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates arXiv [paper][code] #text-adventure #training
[2025/12] Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2025 [paper] #text-adventure #memory
[2025/12] GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators arXiv [paper] #text-adventure
[2025/11] SkillGen: Learning Domain Skills for In-Context Sequential Decision Making arXiv [paper] #text-adventure #prompting
[2025/10] Fine-tuning with RAG for Improving LLM Learning of New Skills arXiv [paper] #text-adventure #planning #memory #training
[2025/10] GenQuest: An LLM-based Text Adventure Game for Language Learners arXiv [paper] #text-adventure #vlm #generation
[2025/10] Constrained Natural Language Action Planning for Resilient Embodied Systems arXiv [paper] #text-adventure #planning #prompting
[2025/10] The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas arXiv [paper] #text-adventure #planning
[2025/10] Graph-Enhanced Policy Optimization in LLM Agent Training arXiv [paper] #text-adventure #planning #training
[2025/10] SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph arXiv [paper] #text-adventure #training
[2025/09] World Model Implanting for Test-time Adaptation of Embodied Agents ICML 2025 poster [paper] #text-adventure #memory #world-model #prompting
[2025/09] Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent arXiv [paper] #text-adventure #planning #multi-agent #self-improvement
[2025/09] Code Driven Planning with Domain-Adaptive Critic arXiv [paper] #text-adventure #planning #self-improvement
[2025/09] Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents arXiv [paper] #text-adventure #training
[2025/09] Reflect before Act: Proactive Error Correction in Language Models arXiv [paper] #text-adventure
[2025/09] Reward Is Enough: LLMs Are In-Context Reinforcement Learners ICLR 2026 Poster [paper] #text-adventure #training #self-improvement
[2025/09] Natural Language PDDL (NL-PDDL) for Open-world Goal-oriented Commonsense Regression Planning in Embodied AI ICLR 2026 Poster [paper] #text-adventure #planning #vlm
[2025/09] Test-Time Mixture of World Models for Embodied Agents in Dynamic Environments ICLR 2026 Poster [paper] #text-adventure #prompting
[2025/09] Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations ICLR 2026 Poster [paper] #text-adventure #training
[2025/09] Dual-Scale World Memory for LLM Agents towards Hard-Exploration Problems ICLR 2026 Poster [paper] #text-adventure
[2025/09] Code Driven Planning with Domain-Adaptive Selector ICLR 2026 Poster [paper] #text-adventure #planning
[2025/09] Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization ICLR 2026 Poster [paper] #text-adventure #memory #training
[2025/09] DreamPhase: Offline Imagination and Uncertainty-Guided Planning for Large-Language-Model Agents ICLR 2026 Poster [paper] #text-adventure #planning #world-model
[2025/09] Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning ICLR 2026 Poster [paper] #text-adventure #tool-use #training
[2025/08] Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2025 [paper] #text-adventure #planning #training #vlm
[2025/07] CoEx -- Co-evolving World-model and Exploration EMNLP 2025 [paper] #text-adventure #planning #world-model
[2025/06] Enhancing Decision-Making of Large Language Models via Actor-Critic ICML 2025 poster [paper] #text-adventure #training
[2025/06] Improving LLM Agent Planning with In-Context Learning via Atomic Fact Augmentation and Lookahead Search arXiv [paper] #text-adventure #planning #world-model #training
[2025/06] StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turns arXiv [paper] #text-adventure #memory
[2025/06] OmniReflect: Discovering Transferable Constitutions for LLM agents via Neuro-Symbolic Reflections arXiv [paper] #text-adventure #planning #training #self-improvement
[2025/06] KnowMap: Efficient Knowledge-Driven Task Adaptation for LLMs arXiv [paper] #text-adventure #training
[2025/05] STORY2GAME: Generating (Almost) Everything in an Interactive Fiction Game arXiv [paper] #text-adventure #generation
[2025/05] LLM-BABYBENCH: Understanding and Evaluating Grounded Planning and Reasoning in LLMs arXiv [paper][code] #text-adventure #planning
[2025/05] Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning ICML 2025 poster [paper] #text-adventure #planning #training
[2025/05] Retrospex: Language Agent Meets Offline Reinforcement Learning Critic EMNLP 2025 [paper] #text-adventure #training
[2025/05] Agent-Environment Alignment via Automated Interface Generation arXiv [paper][code] #text-adventure #tool-use
[2025/05] Divide, Optimize, Merge: Fine-Grained LLM Agent Optimization at Scale arXiv [paper] #text-adventure
[2025/05] Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks NeurIPS 2025 poster [paper] #text-adventure
[2025/05] Learning to Play Like Humans: A Framework for LLM Adaptation in Interactive Fiction Games ACL 2025 [paper] #text-adventure
[2025/05] Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking arXiv [paper] #text-adventure #prompting
[2025/05] SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution arXiv [paper][code] #text-adventure #training
[2025/05] ActiveVOO: Value of Observation Guided Active Knowledge Acquisition for Open-World Embodied Lifted Regression Planning NeurIPS 2025 poster [paper] #text-adventure #planning #prompting #vlm
[2025/05] SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents NeurIPS 2025 poster [paper] #text-adventure #planning #training #self-improvement
[2025/04] TALES: Text Adventure Learning Environment Suite arXiv [paper] #text-adventure
[2025/04] Monte Carlo Planning with Large Language Model for Text-Based Game Agents ICLR 2025 Poster [paper] #text-adventure #planning #training
[2025/04] Group-in-Group Policy Optimization for LLM Agent Training NeurIPS 2025 poster [paper] #text-adventure #training
[2025/03] Haunted House: A text-based game for comparing the flexibility of mental models in humans and LLMs arXiv [paper] #text-adventure
[2025/03] GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks CVPR 2025 [paper] #text-adventure #planning #training #vlm
[2025/02] TextGames: Learning to Self-Play Text-Based Puzzle Games via Language Model Reasoning. arXiv [paper] #text-adventure #self-improvement
[2025/02] Process Reward Models for LLM Agents: Practical Framework and Directions arXiv [paper][code] #text-adventure #training
[2024/12] Fine-tuning large vision-language models as decision-making agents via reinforcement learning NeurIPS 2024 [paper][code] #text-adventure #training #vlm
[2024/09] Discriminator-Guided Embodied Planning for LLM Agent ICLR 2025 Poster [paper] #text-adventure #planning
[2024/09] Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback ICLR 2025 Poster [paper] #text-adventure #planning #training #self-improvement
[2024/07] AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents ACL 2024 [paper][code] #text-adventure #tool-use
[2024/07] Arigraph: Learning knowledge graph world models with episodic memory for llm agents IJCAI 2024 [paper] #text-adventure #planning #memory
[2024/06] Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement EMNLP 2024 [paper][code] #text-adventure #self-improvement
[2024/06] STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models ACL 2024 [paper][code] #text-adventure #training
[2024/05] Agent Planning with World Knowledge Model NeurIPS 2024 [paper][code] #text-adventure #planning #memory #world-model
[2024/05] THREAD: Thinking Deeper with Recursive Spawning NAACL 2024 [paper] #text-adventure #prompting
[2024/05] Policy Improvement using Language Feedback Models NeurIPS 2024 poster [paper] #text-adventure #training
[2024/05] AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning NeurIPS 2024 poster [paper][code] #text-adventure #planning
[2024/04] Learning From Failure: Integrating Negative Examples When Fine-tuning Large Language Models as Agent arXiv [paper][code] #text-adventure #tool-use #training
[2024/04] ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy arXiv [paper] #text-adventure #planning #training #self-improvement
[2024/03] KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents NAACL 2024 [paper][code] #text-adventure #planning
[2024/03] Language Guided Exploration for RL Agents in Text Environments NAACL 2024 [paper][code] #text-adventure #training
[2024/03] Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents ACL 2024 [paper][code] #text-adventure #training #self-improvement
[2024/03] O3D: Offline Data-driven Discovery and Distillation for Sequential Decision-Making with Large Language Models COLM [paper] #text-adventure #training
[2024/03] ReAct Meets ActRe: Autonomous Annotation of Agent Trajectories for Contrastive Self-Training COLM [paper] #text-adventure #planning #training #self-improvement
[2024/03] StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows COLM [paper] #text-adventure #planning #self-improvement
[2024/02] Soft Self-Consistency Improves Language Model Agents arXiv [paper][code] #text-adventure #self-improvement
[2024/02] Empowering Large Language Model Agents through Action Learning COLM [paper][code] #text-adventure #planning #self-improvement
[2023/11] ADaPT: As-Needed Decomposition and Planning with Language Models NAACL 2023 [paper][code] #text-adventure #planning
[2023/10] FireAct: Toward Language Agent Fine-tuning arXiv [paper][code] #text-adventure #training
[2023/10] Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models ICML 2024 [paper][code] #text-adventure #planning #training
[2023/05] SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks NeurIPS 2023 [paper][code] #text-adventure #planning
[2023/04] Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions arXiv [paper] #text-adventure #world-model
[2023/03] Reflexion: Language Agents with Verbal Reinforcement Learning NeurIPS 2023 [paper][code] #text-adventure #training #self-improvement
[2022/10] ReAct: Synergizing Reasoning and Acting in Language Models ICLR 2023 [paper][code] #text-adventure #planning #training
[2022/03] ScienceWorld: Is your Agent Smarter than a 5th Grader? EMNLP 2022 [paper][code] #text-adventure
[2020/10] ALFWorld: Aligning Text and Embodied Environments for Interactive Learning ICLR 2021 [paper][code] #text-adventure #planning
[2019/09] Interactive Fiction Games: A Colossal Adventure AAAI 2020 [paper][code] #text-adventure

communication

[2026/05] Evaluating Large Language Models in a Complex Hidden Role Game arXiv [paper] #communication #planning
[2026/05] QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents arXiv [paper][code] #communication
[2026/05] MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs arXiv [paper] #communication #multi-agent
[2026/05] Playing with Words, Improving with Rewards: Training Language Models for Creative Association arXiv [paper] #communication #training
[2026/04] Trust, Lies, and Long Memories: Emergent Social Dynamics and Reputation in Multi-Round Avalon with LLM Agents arXiv [paper] #communication
[2026/03] Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information arXiv [paper] #communication #role-play
[2026/03] Deception and Communication in Autonomous Multi-Agent Systems: An Experimental Study with Among Us Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2026 [paper] #communication #multi-agent
[2026/01] Hidden in Plain Text: Measuring LLM Deception Quality Against Human Baselines Using Social Deduction Games International Conference on Agents 2027 [paper] #communication #multi-agent
[2026/01] Multicultural Spyfall: Assessing LLMs through Dynamic Multilingual Social Deduction Game arXiv [paper] #communication
[2025/12] WOLF: Werewolf-based Observations for LLM Deception and Falsehoods arXiv [paper] #communication #multi-agent
[2025/12] Measuring Fine-Grained Negotiation Tactics of Humans and LLMs in Diplomacy arXiv [paper] #communication #training
[2025/11] CSP4SDG: Constraint and Information-Theory Based Role Identification in Social Deduction Games with LLM-Enhanced Inference AAAI 2025 [paper] #communication
[2025/11] Multi-agent Undercover Gaming: Hallucination Removal via Counterfactual Test for Multimodal Reasoning arXiv [paper][code] #communication #multi-agent
[2025/10] Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategies arXiv [paper] #communication #multi-agent #self-improvement
[2025/08] Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy AAAI 2025 [paper] #communication #training
[2025/08] What to Ask Next? Probing the Imaginative Reasoning of LLMs with TurtleSoup Puzzles AAAI 2025 [paper] #communication
[2025/08] Ethical Considerations of Large Language Models in Game Playing arXiv [paper] #communication
[2025/07] CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language Games ACL 2025 [paper][code] #communication #multi-agent
[2025/07] Strategy Adaptation in Large Language Model Werewolf Agents arXiv [paper] #communication #prompting
[2025/06] WereWolf-Plus: An Update of Werewolf Game setting Based on DSGBench arXiv [paper][code] #communication #multi-agent
[2025/06] DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy ICML 2025 poster [paper] #communication #training
[2025/05] Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL NeurIPS 2025 poster [paper] #communication #planning #tool-use #training
[2025/01] DVM: Towards Controllable LLM Agents in Social Deduction Games IEEE International Conference on Acoustics, Speech, and Signal Processing 2025 [paper] #communication #training
[2024/12] Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy NeurIPS 2024 [paper][code] #communication #self-improvement
[2024/09] Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search ICLR 2025 Poster [paper] #communication #planning #multi-agent #training
[2024/06] PLAYER: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games arXiv [paper] #communication #multi-agent
[2024/05] Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf NeurIPS 2024 poster [paper] #communication #training
[2024/05] Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy NeurIPS 2024 poster [paper] #communication #planning #multi-agent #self-improvement
[2024/04] Self-playing Adversarial Language Game Enhances LLM Reasoning NeurIPS 2024 [paper][code] #communication #training #self-improvement
[2024/03] Helmsman of the Masses? Evaluate the Opinion Leadership of Large Language Models in the Werewolf Game COLM [paper] #communication #multi-agent
[2024/02] Enhance Reasoning for Large Language Models in the Game Werewolf arXiv [paper] #communication #training
[2024/02] What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based Agents arXiv [paper] #communication
[2024/02] Can Large Language Model Agents Simulate Human Trust Behaviors? NeurIPS 2024 [paper] #communication
[2024/02] Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives ACL 2024 [paper] #communication
[2023/12] Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis AAAI 2024 [paper] #communication
[2023/12] Cooperation on the Fly: Exploring Language Agents for Ad Hoc Teamwork in the Avalon Game arXiv [paper] #communication #multi-agent
[2023/12] Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games ACL 2023 [paper] #communication #multi-agent #prompting
[2023/11] War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars arXiv [paper][code] #communication #multi-agent
[2023/11] clembench: Systematic Evaluation of Chat-Optimized Language Models as Conversational Agents EMNLP 2023 [paper] #communication
[2023/10] Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game ICML 2023 [paper] #communication #training
[2023/10] Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation arXiv [paper] #communication #training
[2023/10] LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay EMNLP 2023 [paper] #communication #multi-agent
[2023/10] Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models arXiv [paper][code] #communication #multi-agent
[2023/10] AvalonBench: Evaluating LLMs Playing the Game of Avalon FMDM@NeurIPS2023 [paper][code] #communication
[2023/09] Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf arXiv [paper] #communication #memory
[2023/08] GameEval: Evaluating LLMs on Conversational Games arXiv [paper][code] #communication
[2022/12] Human-Level Play in the Game of Diplomacy by Combining Language Models with Strategic Reasoning Science [paper] #communication

competition

[2026/06] Doing What They Say, Not What They Reason: Locating the Faithfulness Gap in LLM Agents arXiv [paper] #competition
[2026/06] SMAC-Talk: A Natural Language Extension of the StarCraft Multi-Agent Challenge for Large Language Models arXiv [paper] #competition #multi-agent
[2026/05] GAMBIT: A Three-Mode Benchmark for Adversarial Robustness in Multi-Agent LLM Collectives arXiv [paper] #competition #multi-agent #prompting
[2026/05] Watermarking Game-Playing Agents in Perfect-Information Extensive-Form Games arXiv [paper] #competition
[2026/05] Generalization or Memorization? Brittleness Testing for Chess-Trained Language Models arXiv [paper] #competition #training
[2026/05] PokerSkill: LLMs Can Play Expert-Level Poker without Training or Solvers arXiv [paper][code] #competition #tool-use #prompting
[2026/04] Readable Minds: Emergent Theory-of-Mind-Like Behavior in LLM Poker Agents arXiv [paper] #competition
[2026/04] MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2026 [paper] #competition #multi-agent #training
[2026/03] Grounded Chess Reasoning in Language Models via Master Distillation arXiv [paper] #competition #planning #training
[2026/03] GTO Wizard Benchmark arXiv [paper] #competition #planning #multi-agent #prompting
[2026/03] Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios arXiv [paper] #competition #planning #memory #multi-agent
[2026/02] World Models for Policy Refinement in StarCraft II arXiv [paper] #competition #world-model #prompting
[2026/02] VAM: Verbalized Action Masking for Controllable Exploration in RL Post-Training -- A Chess Case Study arXiv [paper] #competition #training
[2025/12] LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess arXiv [paper] #competition
[2025/12] Beyond Accuracy: A Geometric Stability Analysis of Large Language Models in Chess Evaluation arXiv [paper] #competition
[2025/10] Memory-Augmented State Machine Prompting: A Novel LLM Agent Framework for Real-Time Strategy Games arXiv [paper] #competition #memory
[2025/10] ChessQA: Evaluating Large Language Models for Chess Understanding arXiv [paper] #competition
[2025/10] Out-of-distribution Tests Reveal Compositionality in Chess Transformers arXiv [paper] #competition #planning
[2025/09] HLSMAC: A New StarCraft Multi-Agent Challenge for High-Level Strategic Decision-Making arXiv [paper] #competition #multi-agent #training
[2025/09] Speculative Actions: A Lossless Framework for Faster AI Agents ICLR 2026 Oral [paper] #competition #tool-use
[2025/09] SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning ICLR 2026 Poster [paper] #competition #planning #multi-agent #training
[2025/08] Tracking World States with Language Models: State-Based Evaluation Using Chess arXiv [paper] #competition
[2025/08] SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making Tasks arXiv [paper] #competition #planning #training #self-improvement
[2025/07] Learning to Imitate with Less: Efficient Individual Behavior Modeling in Chess arXiv [paper] #competition
[2025/05] Enfoque Odychess: Un método dialéctico, constructivista y adaptativo para la enseñanza del ajedrez con inteligencias artificiales generativas arXiv [paper] #competition #training
[2025/05] Can Large Language Models Master Complex Card Games? NeurIPS 2025 poster [paper][code] #competition #training
[2025/04] Explore the Reasoning Capability of LLMs in the Chess Testbed NAACL 2025 [paper] #competition
[2025/04] ZeroSumEval: Scaling LLM Evaluation with Inter-Model Competition arXiv [paper][code] #competition #planning
[2025/04] LLM-PySC2: Starcraft II learning environment for Large Language Models NeurIPS 2025 poster [paper] #competition #planning #multi-agent #vlm
[2025/04] The PokeAgent Challenge: Competitive and Long Context Learning at Scale NeurIPS Competition Track 2025 [paper] #competition
[2025/03] Society of Mind Meets Real-Time Strategy: A Hierarchical Multi-Agent Framework for Strategic Reasoning COLM 2025 [paper] #competition #multi-agent #training
[2025/02] Hierarchical Expert Prompt for Large-Language-Model: An Approach Defeat Elite AI in TextStarCraft II for the First Time arXiv [paper][code] #competition
[2025/02] Implicit Search via Discrete Diffusion: A Study on Chess ICLR 2025 Poster [paper][code] #competition #planning
[2025/01] POKERBENCH: Training Large Language Models to become Professional Poker Players AAAI 2025 [paper] #competition #planning #training
[2025/01] Complete Chess Games Enable LLM Become A Chess Master NAACL 2025 [paper] #competition #training
[2025/01] Mastering Board Games by External and Internal Planning with Language Models ICML 2025 spotlightposter [paper] #competition #planning
[2025/01] Language Models as Implicit Tree Search ICML 2025 poster [paper] #competition #planning #training
[2024/10] PokéChamp: An Expert-level Minimax Language Agent ICML 2025 [paper][code] #competition #planning
[2024/08] Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information 2024 IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) 2024 [paper] #competition #planning #multi-agent #training
[2024/05] Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models NeurIPS 2024 poster [paper] #competition
[2024/05] Reflective Multi-Agent Collaboration based on Large Language Models NeurIPS 2024 poster [paper] #competition #planning #multi-agent #training
[2024/03] Embodied LLM Agents Learn to Cooperate in Organized Teams IEEE Transactions on Computational Social Systems 2024 [paper] #competition #planning #multi-agent
[2024/02] PokéLLMon: A Human-Parity Agent for Pokémon Battles with Large Language Models TOIT 2025 [paper][code] #competition #training
[2024/02] Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization ACL 2024 [paper][code] #competition #training
[2024/01] PokerGPT: An End-to-End Lightweight Solver for Multi-Player Texas Hold'em via Large Language Model arXiv [paper] #competition #training
[2024/01] SwarmBrain: Embodied agent for real-time strategy game StarCraft II via large language models arXiv [paper] #competition #training
[2023/12] Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach NeurIPS 2024 poster [paper][code] #competition #planning
[2023/09] Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4 COLM 2024 [paper] #competition #planning #memory #prompting
[2023/08] Are ChatGPT and GPT-4 Good Poker Players?--A Pre-Flop Analysis arXiv [paper] #competition
[2023/06] ChessGPT: Bridging Policy Learning and Language Modeling NeurIPS 2023 [paper][code] #competition
[2022/10] Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task ICLR 2023 [paper] #competition

cooperation

[2026/04] Don't Make the LLM Read the Graph: Make the Graph Think arXiv [paper] #cooperation #multi-agent
[2026/03] On the Strengths and Weaknesses of Data for Open-set Embodied Assistance arXiv [paper] #cooperation #training
[2025/12] ReCollab: Retrieval-Augmented LLMs for Cooperative Ad-hoc Teammate Modeling arXiv [paper] #cooperation #memory
[2025/10] LLM-Hanabi: Evaluating Multi-Agent Gameplays with Theory-of-Mind and Rationale Inference in Imperfect Information Collaboration Game arXiv [paper] #cooperation #multi-agent
[2025/08] CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning arXiv [paper] #cooperation #planning #multi-agent #training
[2025/06] PSALM-V: Automating Symbolic Planning in Interactive Visual Environments with Large Language Models arXiv [paper] #cooperation #planning #multi-agent
[2024/05] Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration ACL 2024 [paper][code] #cooperation #planning #multi-agent #training
[2024/03] Can LLM-Augmented Autonomous Agents Cooperate?, An Evaluation of Their Cooperative Capabilities through Melting Pot IEEE Transactions on Artificial Intelligence 2024 [paper] #cooperation #multi-agent
[2024/03] ProAgent: Building Proactive Cooperative Agents with Large Language Models AAAI 2024 [paper] #cooperation
[2024/02] S-Agents: Self-organizing Agents in Open-ended Environments arXiv [paper] #cooperation
[2023/12] LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination AAMAS 2023 [paper] #cooperation
[2023/10] Evaluating Multi-agent Coordination Abilities in Large Language Models NAACL 2023 [paper] #cooperation #planning #multi-agent #prompting
[2023/10] Theory of Mind for Multi-Agent Collaboration via Large Language Models EMNLP 2023 [paper][code] #cooperation #planning #multi-agent #training
[2023/09] MindAgent: Emergent Gaming Interaction NAACL 2023 [paper] #cooperation #planning #multi-agent #prompting
[2023/07] Building Cooperative Embodied Agents Modularly with Large Language Models ICLR 2024 [paper][code] #cooperation #planning #multi-agent #training

[2026/06] Can LLM Agents Sustain Long-Horizon Organizational Dynamics? arXiv [paper] #sim-social #planning #multi-agent
[2026/06] Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social Simulation arXiv [paper] #sim-social #multi-agent
[2026/05] GASim: A Graph-Accelerated Hybrid Framework for Social Simulation arXiv [paper][code] #sim-social #memory #multi-agent
[2026/05] ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic Profiles arXiv [paper] #sim-social #memory #multi-agent
[2026/05] ALSO: Adversarial Online Strategy Optimization for Social Agents arXiv [paper] #sim-social #multi-agent #training
[2026/05] PAVE: A Cognitive Architecture for Legitimate Violation in Generative Agent Societies arXiv [paper] #sim-social #role-play
[2026/05] APS: Bias-Controlled Adaptive Prototype Simulation for Population-Scale LLM Agents arXiv [paper] #sim-social
[2026/04] LLM-Agent-based Social Simulation for Attitude Diffusion arXiv [paper] #sim-social #memory
[2026/04] Restoring Heterogeneity in LLM-based Social Simulation: An Audience Segmentation Approach arXiv [paper] #sim-social #role-play
[2026/04] SLALOM: Simulation Lifecycle Analysis via Longitudinal Observation Metrics for Social Simulation arXiv [paper] #sim-social
[2026/04] RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents arXiv [paper] #sim-social #planning
[2026/04] Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing Agents arXiv [paper] #sim-social
[2026/04] Auditing Support Strategies in LLMs through Grounded Multi-Turn Social Simulation arXiv [paper] #sim-social
[2026/03] PolicySim: An LLM-Based Agent Social Simulation Sandbox for Proactive Policy Optimization WWW 2026 [paper] #sim-social #training
[2026/03] Belief-Driven Multi-Agent Collaboration via Approximate Perfect Bayesian Equilibrium for Social Simulation WWW 2026 [paper][code] #sim-social #multi-agent
[2026/02] AIvilization v0: Toward Large-Scale Artificial Social Simulation with a Unified Agent Architecture and Adaptive Agent Profiles arXiv [paper] #sim-social #planning
[2026/02] Exploring Silicon-Based Societies: An Early Study of the Moltbook Agent Community arXiv [paper] #sim-social
[2026/02] Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook Proceedings of the ACM Conference on AI and Agentic Systems 2026 [paper] #sim-social
[2026/02] The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies arXiv [paper] #sim-social #multi-agent #self-improvement
[2026/01] When Agents See Humans as the Outgroup: Belief-Dependent Bias in LLM-Powered Agents arXiv [paper] #sim-social #multi-agent
[2026/01] MARO: Learning Stronger Reasoning from Social Interaction arXiv [paper] #sim-social #multi-agent
[2026/01] HumanLLM: Towards Personalized Understanding and Simulation of Human Nature arXiv [paper] #sim-social #training
[2025/12] EZYer: A simulacrum of high school with generative agent arXiv [paper] #sim-social #memory
[2025/12] Agent-Kernel: A MicroKernel Multi-Agent System Framework for Adaptive Social Simulation Powered by LLMs arXiv [paper] #sim-social #multi-agent
[2025/10] Multimodal Safety Evaluation in Generative Agent Social Simulations arXiv [paper] #sim-social #planning #vlm
[2025/10] Alita-G: Self-Evolving Generative Agent for Agent Generation arXiv [paper] #sim-social #memory #self-improvement
[2025/10] Doing Things with Words: Rethinking Theory of Mind Simulation in Large Language Models Computational Linguistics 2025 [paper] #sim-social
[2025/10] Social Simulations with Large Language Model Risk Utopian Illusion arXiv [paper] #sim-social #multi-agent
[2025/10] Emergent Coordinated Behaviors in Networked LLM Agents: Modeling the Strategic Dynamics of Information Operations WWW 2025 [paper] #sim-social
[2025/09] Implicit Behavioral Alignment of Language Agents in High-Stakes Crowd Simulations EMNLP 2025 [paper] #sim-social #role-play
[2025/09] The Emergence of Altruism in Large-Language-Model Agents Society arXiv [paper] #sim-social
[2025/07] LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra arXiv [paper][code] #sim-social #multi-agent #training #role-play
[2025/07] Too Human to Model:The Uncanny Valley of LLMs in Social Simulation -- When Generative Language Agents Misalign with Modelling Principles arXiv [paper] #sim-social
[2025/07] Validating Generative Agent-Based Models of Social Norm Enforcement: From Replication to Novel Predictions Annual Meeting of the Cognitive Science Society 2025 [paper] #sim-social #role-play
[2025/06] Empowering Economic Simulation for Massively Multiplayer Online Games through Generative Agent-Based Modeling KDD 2025 [paper] #sim-social #training
[2025/06] IndoorWorld: Integrating Physical Task Solving and Social Simulation in A Heterogeneous Multi-Agent Environment EMNLP 2025 [paper] #sim-social #multi-agent
[2025/06] AgentGroupChat-V2: Divide-and-Conquer Is What LLM-Based Multi-Agent System Need arXiv [paper][code] #sim-social #planning #multi-agent
[2025/06] Infected Smallville: How Disease Threat Shapes Sociality in LLM Agents arXiv [paper] #sim-social
[2025/05] EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation EMNLP 2025 [paper] #sim-social #role-play
[2025/04] SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation NAACL 2025 [paper] #sim-social #planning
[2025/04] BookWorld: From Novels to Interactive Agent Societies for Creative Story Generation arXiv [paper] #sim-social #multi-agent #generation
[2025/04] MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework NeurIPS 2025 poster [paper] #sim-social #planning #training
[2025/03] The Impact of Big Five Personality Traits on AI Agent Decision-Making in Public Spaces: A Social Simulation Study arXiv [paper] #sim-social
[2025/02] Investigating and Extending Homans' Social Exchange Theory with Large Language Model based Agents ACL 2025 [paper][code] #sim-social
[2025/01] Simulating Human-like Daily Activities with Desire-driven Autonomy ICLR 2025 [paper][code] #sim-social
[2025/01] Are Human Interactions Replicable by Generative Agents? A Case Study on Pronoun Usage in Hierarchical Interactions arXiv [paper] #sim-social
[2024/10] Project Sid: Many-agent simulations toward AI civilization arXiv [paper] #sim-social
[2024/06] Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theory arXiv [paper] #sim-social #multi-agent
[2024/05] Agent hospital: A simulacrum of hospital with evolvable medical agents arXiv [paper] #sim-social #planning
[2024/03] SOTOPIA-$\pi$: Interactive Learning of Socially Intelligent Language Agents ACL 2024 [paper][code] #sim-social #training
[2023/10] Humanoid Agents: Platform for Simulating Human-like Generative Agents EMNLP 2023 [paper] #sim-social
[2023/10] Lyfe Agents: Generative agents for low-cost real-time social interactions arXiv [paper] #sim-social #memory #multi-agent #self-improvement
[2023/10] SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents ICLR 2023 [paper][code] #sim-social #role-play
[2023/08] AgentSims: An Open-Source Sandbox for Large Language Model Evaluation arXiv [paper][code] #sim-social #planning #tool-use
[2023/07] S3: Social-network Simulation System with Large Language Model-Empowered Agents arXiv [paper] #sim-social #prompting
[2023/04] Generative Agents: Interactive Simulacra of Human Behavior UIST 2023 [paper][code] #sim-social

sim-embodied

[2026/05] Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty arXiv [paper] #sim-embodied #training
[2026/05] Probing Embodied LLMs: When Higher Observation Fidelity Hurts Problem Solving arXiv [paper] #sim-embodied
[2026/02] To Move or Not to Move: Constraint-based Planning Enables Zero-Shot Generalization for Interactive Navigation arXiv [paper] #sim-embodied #planning #prompting #vlm
[2025/12] Emergence: Overcoming Privileged Information Bias in Asymmetric Embodied Agents via Active Querying arXiv [paper] #sim-embodied
[2025/12] ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning arXiv [paper] #sim-embodied #planning #memory #training
[2025/12] HELP: Hierarchical Embodied Language Planner for Household Tasks arXiv [paper] #sim-embodied #planning
[2025/11] DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration arXiv [paper] #sim-embodied #planning #multi-agent #world-model
[2025/11] MADRA: Multi-Agent Debate for Risk-Aware Embodied Planning arXiv [paper] #sim-embodied #planning #multi-agent #prompting
[2025/09] ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures ICLR 2026 Poster [paper] #sim-embodied #planning
[2024/09] Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems ICLR 2025 Poster [paper] #sim-embodied #training
[2024/09] BadRobot: Jailbreaking Embodied LLM Agents in the Physical World ICLR 2025 Poster [paper] #sim-embodied #planning #vlm
[2024/09] GameGen-X: Interactive Open-world Game Video Generation ICLR 2025 Poster [paper][code] #sim-embodied #vlm
[2024/01] True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning arXiv [paper][code] #sim-embodied #training
[2023/10] Octopus: Embodied Vision-Language Programmer from Environmental Feedback ECCV 2023 [paper][code] #sim-embodied #planning #training #vlm
[2023/05] Language Models Meet World Models: Embodied Experiences Enhance Language Models NeurIPS 2023 [paper][code] #sim-embodied #planning #world-model
[2022/12] LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models ICCV 2023 [paper] #sim-embodied #planning #prompting
[2022/01] Language Models as Zero-ShoSSocial-network Simulation Planners: Extracting Actionable Knowledge for Embodied Agents ICML 2022 [paper][code] #sim-embodied

sim-other

[2024/01] CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents ICLR 2024 [paper][code] #sim-other

crafter

[2025/09] Goal-Guided Efficient Exploration via Large Language Model in Reinforcement Learning arXiv [paper] #crafter #planning #training
[2025/08] HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents arXiv [paper] #crafter #planning #training
[2025/06] Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback arXiv [paper] #crafter #self-improvement
[2025/02] LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning arXiv [paper] #crafter #planning #memory #multi-agent
[2024/10] Mars: Situated Inductive Reasoning in an Open-World Environment NeurIPS 2024 [paper] #crafter
[2024/07] Enhancing Agent Learning through World Dynamics Modeling EMNLP 2024 [paper] #crafter
[2024/04] AgentKit: Flow Engineering with Graphs, not Coding arXiv [paper][code] #crafter #planning
[2024/04] World Models with Hints of Large Language Models for Goal Achieving NAACL 2024 [paper] #crafter #training #vlm
[2024/03] EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents COLM [paper] #crafter #training
[2024/03] AgentKit: Structured LLM Reasoning with Dynamic Graphs COLM [paper] #crafter #planning
[2023/09] AdaRefiner: Refining Decisions of Language Models with Adaptive Feedback NAACL 2023 [paper] #crafter #training
[2023/06] OMNI: Open-endedness via Models of human Notions of Interestingness arXiv [paper][code] #crafter
[2023/05] SPRING: Studying Papers and Reasoning to play Games NeurIPS 2023 [paper] #crafter
[2023/02] Guiding Pretraining in Reinforcement Learning with Large Language Models ICML 2023 [paper] #crafter #training

action

[2026/05] Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning arXiv [paper] #action #training #vlm
[2026/05] ANO: A Principled Approach to Robust Policy Optimization arXiv [paper] #action #training
[2026/05] Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay arXiv [paper] #action #planning #training #vlm
[2026/04] Playing DOOM with 1.3M Parameters: Specialized Small Models vs Large Language Models for Real-Time Game Control arXiv [paper] #action
[2026/04] PokeGym: A Visually-Driven Long-Horizon Benchmark for Vision-Language Models arXiv [paper] #action #planning #vlm
[2026/04] GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning arXiv [paper] #action #training
[2026/03] Understanding the Challenges in Iterative Generative Optimization with LLMs arXiv [paper] #action
[2026/03] See, Symbolize, Act: Grounding VLMs with Spatial Representations for Better Gameplay arXiv [paper] #action #vlm
[2026/02] Implicit Strategic Optimization: Rethinking Long-Horizon Decision-Making in Adversarial Poker Environments arXiv [paper] #action #training
[2025/12] Robust Agents in Open-Ended Worlds arXiv [paper] #action #multi-agent #training #generation
[2025/09] Exploration with Foundation Models: Capabilities, Limitations, and Hybrid Approaches arXiv [paper] #action #training #vlm
[2025/08] A Multi-Agent Pokemon Tournament for Evaluating Strategic Reasoning of Large Language Models arXiv [paper] #action #multi-agent
[2025/08] Learning Game-Playing Agents with Generative Code Optimization arXiv [paper] #action #training #self-improvement
[2025/05] Frog Soup: Zero-Shot, In-Context, and Sample-Efficient Frogger Agents arXiv [paper][code] #action #training
[2025/05] Multiple Weaks Win Single Strong: Large Language Models Ensemble Weak Reinforcement Learning Agents into a Supreme One arXiv [paper] #action #training
[2025/05] Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs NeurIPS 2025 poster [paper] #action #training
[2025/05] LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models NeurIPS 2025 spotlight [paper][code] #action #training
[2025/05] PoE-World: Compositional World Modeling with Products of Programmatic Experts NeurIPS 2025 spotlight [paper] #action #planning #world-model
[2025/04] Better Decisions through the Right Causal World Model arXiv [paper] #action #planning #world-model #training
[2025/01] LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations ICML 2025 poster [paper] #action #planning #training
[2024/10] Unbounded: A Generative Infinite Game of Character Life Simulation ICLR 2024 [paper] #action
[2024/09] Can VLMs Play Action Role-Playing Games? Take Black Myth Wukong as a Study Case arXiv [paper][code] #action #planning #training
[2024/09] MaestroMotif: Skill Design from Artificial Intelligence Feedback ICLR 2025 Oral [paper] #action #training
[2024/09] BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games ICLR 2025 Poster [paper] #action #planning #training #vlm
[2024/08] Atari-GPT: Investigating the Capabilities of Multimodal Large Language Models as Low-Level Policies for Atari Games arXiv [paper] #action #planning #training
[2024/07] Baba Is AI: Break the Rules to Beat the Benchmark ICML 2024 [paper] #action #vlm
[2024/03] Will GPT-4 Run DOOM? IEEE Transactions on Games 2024 [paper][code] #action #planning #training
[2024/03] Evaluate LLMs in Real Time with Street Fighter III GitHub [paper][code] #action
[2023/02] Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning ICML 2023 [paper][code] #action #training

video-adventure

[2024/03] Cradle: Empowering Foundation Agents Towards General Computer Control ICML 2024 [paper][code] #video-adventure #planning
[2024/03] Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents 2024 IEEE Conference on Games (CoG) 2024 [paper][code] #video-adventure #planning #prompting
[2023/09] Motif: Intrinsic Motivation from Artificial Intelligence Feedback ICLR 2024 [paper][code] #video-adventure #training

benchmark

[2026/01] NitroGen: An Open Foundation Model for Generalist Gaming Agents arXiv [paper] #benchmark #training
[2025/10] Think Globally, Group Locally: Evaluating LLMs Using Multi-Lingual Word Grouping Games EMNLP 2025 [paper] #benchmark
[2025/06] Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games arXiv [paper][code] #benchmark #training
[2025/06] UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI ICCV 2025 [paper][code] #benchmark #multi-agent #training
[2025/05] lmgame-Bench: How Good are LLMs at Playing Games?." ICLR 2026 Poster [paper][code] #benchmark #planning #training
[2025/05] Is Your LLM Really Mastering the Concept? A Multi-Agent Benchmark arXiv [paper][code] #benchmark #multi-agent

other

[2026/04] GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents arXiv [paper] #planning #vlm
[2026/04] Nemobot Games: Crafting Strategic AI Gaming Agents for Interactive Learning with Large Language Models arXiv [paper] #tool-use #training #self-improvement
[2026/04] From World-Gen to Quest-Line: A Dependency-Driven Prompt Pipeline for Coherent RPG Generation arXiv [paper] #planning #generation
[2026/03] Sensi: Learn One Thing at a Time -- Curriculum-Based Test-Time Learning for LLM Game Agents arXiv [paper]
[2026/02] VLM-Guided Experience Replay arXiv [paper] #planning #training #vlm
[2026/01] SNAP: A Plan-Driven Framework for Controllable Interactive Narrative Generation arXiv [paper] #planning #generation
[2025/10] ROBOPSY PL[AI]: Using Role-Play to Investigate how LLMs Present Collective Memory arXiv [paper] #role-play
[2025/08] All Stories Are One Story: Emotional Arc Guided Procedural Game Level Generation arXiv [paper] #generation
[2025/08] CHBench: A Cognitive Hierarchy Benchmark for Evaluating Strategic Reasoning Capability of LLMs arXiv [paper] #memory
[2025/06] The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind arXiv [paper] #multi-agent #training
[2025/04] PAYADOR: A Minimalist Approach to Grounding Language Models on Structured Data for Interactive Storytelling and Role-playing Games arXiv [paper]
[2025/04] Enhancing Player Enjoyment with a Two-Tier DRL and LLM-Based Agent System for Fighting Games arXiv [paper] #training
[2025/03] Playing games with Large language models: Randomness and strategy arXiv [paper] #multi-agent
[2025/03] Collaborative Storytelling and LLM: A Linguistic Analysis of Automatically-Generated Role-Playing Game Sessions arXiv [paper]
[2025/03] Cultivating Game Sense for Yourself: Making VLMs Gaming Experts arXiv [paper] #vlm
[2025/02] RPGBENCH: Evaluating Large Language Models as Role-Playing Game Engines arXiv [paper]
[2025/02] Hybrid Voting-Based Task Assignment in Role-Playing Games arXiv [paper] #planning
[2024/09] Agents' Room: Narrative Generation through Multi-step Collaboration ICLR 2025 Poster [paper] #generation
[2024/07] What if Red Can Talk? Dynamic Dialogue Generation Using Large Language Models. arXiv [paper] #generation
[2023/10] Language as reality: a co-creative storytelling game experience in 1001 nights using generative AI. AAAI 2023 [paper] #generation

By Mechanism

The same papers as above, re-grouped by agent design. A paper with multiple Mechanism tags appears in each relevant section.

planning

[2026/06] Can LLM Agents Sustain Long-Horizon Organizational Dynamics? arXiv [paper] #sim-social #planning #multi-agent
[2026/06] From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents arXiv [paper] #text-adventure #planning
[2026/05] From History to State: Constant-Context Skill Learning for LLM Agents arXiv [paper] #text-adventure #planning #training
[2026/05] PriorZero: Bridging Language Priors and World Models for Decision Making arXiv [paper][code] #text-adventure #planning #world-model #training
[2026/05] Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay arXiv [paper] #action #planning #training #vlm
[2026/05] APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents arXiv [paper] #text-adventure #planning #self-improvement
[2026/05] Evaluating Large Language Models in a Complex Hidden Role Game arXiv [paper] #communication #planning
[2026/05] SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems arXiv [paper] #text-adventure #planning #memory #tool-use
[2026/04] Aligning Progress and Feasibility: A Neuro-Symbolic Dual Memory Framework for Long-Horizon LLM Agents arXiv [paper] #text-adventure #planning #memory
[2026/04] GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents arXiv [paper] #planning #vlm
[2026/04] PokeGym: A Visually-Driven Long-Horizon Benchmark for Vision-Language Models arXiv [paper] #action #planning #vlm
[2026/04] RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents arXiv [paper] #sim-social #planning
[2026/04] DORA Explorer: Improving the Exploration Ability of LLMs Without Training arXiv [paper] #text-adventure #planning #prompting
[2026/04] From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents arXiv [paper] #text-adventure #planning
[2026/04] Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows arXiv [paper] #text-adventure #planning #memory #multi-agent
[2026/04] From World-Gen to Quest-Line: A Dependency-Driven Prompt Pipeline for Coherent RPG Generation arXiv [paper] #planning #generation
[2026/04] GraSP: Graph-Structured Skill Compositions for LLM Agents arXiv [paper] #text-adventure #planning #memory #self-improvement
[2026/03] RPMS: Enhancing LLM-Based Embodied Planning through Rule-Augmented Memory Synergy arXiv [paper] #text-adventure #planning #memory
[2026/03] Grounded Chess Reasoning in Language Models via Master Distillation arXiv [paper] #competition #planning #training
[2026/03] GTO Wizard Benchmark arXiv [paper] #competition #planning #multi-agent #prompting
[2026/03] Reward Prediction with Factorized World States arXiv [paper] #text-adventure #planning #prompting
[2026/03] Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios arXiv [paper] #competition #planning #memory #multi-agent
[2026/02] VLM-Guided Experience Replay arXiv [paper] #planning #training #vlm
[2026/02] Active Epistemic Control for Query-Efficient Verified Planning arXiv [paper] #text-adventure #planning
[2026/02] AIvilization v0: Toward Large-Scale Artificial Social Simulation with a Unified Agent Architecture and Adaptive Agent Profiles arXiv [paper] #sim-social #planning
[2026/02] Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents arXiv [paper] #text-adventure #planning #training
[2026/02] TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agents arXiv [paper] #text-adventure #planning
[2026/02] To Move or Not to Move: Constraint-based Planning Enables Zero-Shot Generalization for Interactive Navigation arXiv [paper] #sim-embodied #planning #prompting #vlm
[2026/02] CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent Pipelines arXiv [paper] #text-adventure #planning #world-model #training
[2026/01] Beyond Entangled Planning: Task-Decoupled Planning for Long-Horizon Agents arXiv [paper] #text-adventure #planning #prompting
[2026/01] SNAP: A Plan-Driven Framework for Controllable Interactive Narrative Generation arXiv [paper] #planning #generation
[2026/01] Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents arXiv [paper] #text-adventure #planning #training
[2025/12] ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning arXiv [paper] #sim-embodied #planning #memory #training
[2025/12] HELP: Hierarchical Embodied Language Planner for Household Tasks arXiv [paper] #sim-embodied #planning
[2025/11] DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration arXiv [paper] #sim-embodied #planning #multi-agent #world-model
[2025/11] MADRA: Multi-Agent Debate for Risk-Aware Embodied Planning arXiv [paper] #sim-embodied #planning #multi-agent #prompting
[2025/10] Fine-tuning with RAG for Improving LLM Learning of New Skills arXiv [paper] #text-adventure #planning #memory #training
[2025/10] Constrained Natural Language Action Planning for Resilient Embodied Systems arXiv [paper] #text-adventure #planning #prompting
[2025/10] The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas arXiv [paper] #text-adventure #planning
[2025/10] Multimodal Safety Evaluation in Generative Agent Social Simulations arXiv [paper] #sim-social #planning #vlm
[2025/10] Graph-Enhanced Policy Optimization in LLM Agent Training arXiv [paper] #text-adventure #planning #training
[2025/10] Out-of-distribution Tests Reveal Compositionality in Chess Transformers arXiv [paper] #competition #planning
[2025/09] Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent arXiv [paper] #text-adventure #planning #multi-agent #self-improvement
[2025/09] Code Driven Planning with Domain-Adaptive Critic arXiv [paper] #text-adventure #planning #self-improvement
[2025/09] Goal-Guided Efficient Exploration via Large Language Model in Reinforcement Learning arXiv [paper] #crafter #planning #training
[2025/09] Natural Language PDDL (NL-PDDL) for Open-world Goal-oriented Commonsense Regression Planning in Embodied AI ICLR 2026 Poster [paper] #text-adventure #planning #vlm
[2025/09] Experience-based Knowledge Correction for Robust Planning in Minecraft ICLR 2026 Poster [paper] #minecraft #planning
[2025/09] SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning ICLR 2026 Poster [paper] #competition #planning #multi-agent #training
[2025/09] Code Driven Planning with Domain-Adaptive Selector ICLR 2026 Poster [paper] #text-adventure #planning
[2025/09] ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures ICLR 2026 Poster [paper] #sim-embodied #planning
[2025/09] DreamPhase: Offline Imagination and Uncertainty-Guided Planning for Large-Language-Model Agents ICLR 2026 Poster [paper] #text-adventure #planning #world-model
[2025/08] CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks Findings of EMNLP 2025 [paper] #minecraft #planning #multi-agent
[2025/08] Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2025 [paper] #text-adventure #planning #training #vlm
[2025/08] CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning arXiv [paper] #cooperation #planning #multi-agent #training
[2025/08] SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making Tasks arXiv [paper] #competition #planning #training #self-improvement
[2025/08] HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents arXiv [paper] #crafter #planning #training
[2025/07] CoEx -- Co-evolving World-model and Exploration EMNLP 2025 [paper] #text-adventure #planning #world-model
[2025/06] Optimus-3: Towards Generalist Multimodal Minecraft Agents with Scalable Task Experts arXiv [paper][code] #minecraft #planning
[2025/06] Improving LLM Agent Planning with In-Context Learning via Atomic Fact Augmentation and Lookahead Search arXiv [paper] #text-adventure #planning #world-model #training
[2025/06] OmniReflect: Discovering Transferable Constitutions for LLM agents via Neuro-Symbolic Reflections arXiv [paper] #text-adventure #planning #training #self-improvement
[2025/06] AgentGroupChat-V2: Divide-and-Conquer Is What LLM-Based Multi-Agent System Need arXiv [paper][code] #sim-social #planning #multi-agent
[2025/06] PSALM-V: Automating Symbolic Planning in Interactive Visual Environments with Large Language Models arXiv [paper] #cooperation #planning #multi-agent
[2025/05] Don’t Just Follow MLLM Plans: Robust and Efficient Planning for Open-World Agents arXiv [paper] #minecraft #planning #vlm
[2025/05] Knowledge Retrieval in LLM Gaming: A Shift from Entity-Centric to Goal-Oriented Graphs Knowledge-Based Systems 2025 [paper] #minecraft #planning #memory
[2025/05] lmgame-Bench: How Good are LLMs at Playing Games?." ICLR 2026 Poster [paper][code] #benchmark #planning #training
[2025/05] LLM-BABYBENCH: Understanding and Evaluating Grounded Planning and Reasoning in LLMs arXiv [paper][code] #text-adventure #planning
[2025/05] Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning ICML 2025 poster [paper] #text-adventure #planning #training
[2025/05] ActiveVOO: Value of Observation Guided Active Knowledge Acquisition for Open-World Embodied Lifted Regression Planning NeurIPS 2025 poster [paper] #text-adventure #planning #prompting #vlm
[2025/05] Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL NeurIPS 2025 poster [paper] #communication #planning #tool-use #training
[2025/05] SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents NeurIPS 2025 poster [paper] #text-adventure #planning #training #self-improvement
[2025/05] PoE-World: Compositional World Modeling with Products of Programmatic Experts NeurIPS 2025 spotlight [paper] #action #planning #world-model
[2025/05] WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents NeurIPS 2025 poster [paper] #minecraft #planning #world-model #prompting
[2025/04] WALL-E 2.0: World Alignment by NeuroSymbolic Learning Improves World Model-based LLM Agents arXiv [paper][code] #minecraft #planning #world-model #prompting
[2025/04] Better Decisions through the Right Causal World Model arXiv [paper] #action #planning #world-model #training
[2025/04] ZeroSumEval: Scaling LLM Evaluation with Inter-Model Competition arXiv [paper][code] #competition #planning
[2025/04] SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation NAACL 2025 [paper] #sim-social #planning
[2025/04] Monte Carlo Planning with Large Language Model for Text-Based Game Agents ICLR 2025 Poster [paper] #text-adventure #planning #training
[2025/04] LLM-PySC2: Starcraft II learning environment for Large Language Models NeurIPS 2025 poster [paper] #competition #planning #multi-agent #vlm
[2025/04] MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework NeurIPS 2025 poster [paper] #sim-social #planning #training
[2025/03] Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems arXiv [paper] #minecraft #planning #multi-agent #tool-use
[2025/03] GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks CVPR 2025 [paper] #text-adventure #planning #training #vlm
[2025/03] Plancraft: an evaluation dataset for planning with LLM agents COLM 2025 [paper] #minecraft #planning #memory #tool-use
[2025/02] Optimus-2: Multimodal World Model for Open-World Minecraft Agents CVPR 2025 [paper][code] #minecraft #planning #world-model #vlm
[2025/02] LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning arXiv [paper] #crafter #planning #memory #multi-agent
[2025/02] Hybrid Voting-Based Task Assignment in Role-Playing Games arXiv [paper] #planning
[2025/02] Implicit Search via Discrete Diffusion: A Study on Chess ICLR 2025 Poster [paper][code] #competition #planning
[2025/01] POKERBENCH: Training Large Language Models to become Professional Poker Players AAAI 2025 [paper] #competition #planning #training
[2025/01] Mastering Board Games by External and Internal Planning with Language Models ICML 2025 spotlightposter [paper] #competition #planning
[2025/01] LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations ICML 2025 poster [paper] #action #planning #training
[2025/01] Language Models as Implicit Tree Search ICML 2025 poster [paper] #competition #planning #training
[2024/10] WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents arXiv [paper][code] #minecraft #planning #world-model
[2024/10] ADAM: An Embodied Causal Agent in Open-World Environments ICLR 2025 [paper][code] #minecraft #planning
[2024/10] PokéChamp: An Expert-level Minimax Language Agent ICML 2025 [paper][code] #competition #planning
[2024/09] Can VLMs Play Action Role-Playing Games? Take Black Myth Wukong as a Study Case arXiv [paper][code] #action #planning #training
[2024/09] Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search ICLR 2025 Poster [paper] #communication #planning #multi-agent #training
[2024/09] Discriminator-Guided Embodied Planning for LLM Agent ICLR 2025 Poster [paper] #text-adventure #planning
[2024/09] Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback ICLR 2025 Poster [paper] #text-adventure #planning #training #self-improvement
[2024/09] BadRobot: Jailbreaking Embodied LLM Agents in the Physical World ICLR 2025 Poster [paper] #sim-embodied #planning #vlm
[2024/09] BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games ICLR 2025 Poster [paper] #action #planning #training #vlm
[2024/08] Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-horizon Tasks NeurIPS 2024 [paper][code] #minecraft #planning #memory #prompting
[2024/08] Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information 2024 IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) 2024 [paper] #competition #planning #multi-agent #training
[2024/08] Atari-GPT: Investigating the Capabilities of Multimodal Large Language Models as Low-Level Policies for Atari Games arXiv [paper] #action #planning #training
[2024/07] Arigraph: Learning knowledge graph world models with episodic memory for llm agents IJCAI 2024 [paper] #text-adventure #planning #memory
[2024/07] Odyssey: Empowering Agents with Open-World Skills. IJCAI 2024 [paper][code] #minecraft #planning #tool-use
[2024/06] VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft Findings of ACL 2024 [paper][code] #minecraft #planning #multi-agent
[2024/05] Agent Planning with World Knowledge Model NeurIPS 2024 [paper][code] #text-adventure #planning #memory #world-model
[2024/05] Agent hospital: A simulacrum of hospital with evolvable medical agents arXiv [paper] #sim-social #planning
[2024/05] Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration ACL 2024 [paper][code] #cooperation #planning #multi-agent #training
[2024/05] Reflective Multi-Agent Collaboration based on Large Language Models NeurIPS 2024 poster [paper] #competition #planning #multi-agent #training
[2024/05] AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning NeurIPS 2024 poster [paper][code] #text-adventure #planning
[2024/05] Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy NeurIPS 2024 poster [paper] #communication #planning #multi-agent #self-improvement
[2024/04] ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy arXiv [paper] #text-adventure #planning #training #self-improvement
[2024/04] AgentKit: Flow Engineering with Graphs, not Coding arXiv [paper][code] #crafter #planning
[2024/03] KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents NAACL 2024 [paper][code] #text-adventure #planning
[2024/03] Cradle: Empowering Foundation Agents Towards General Computer Control ICML 2024 [paper][code] #video-adventure #planning
[2024/03] Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents 2024 IEEE Conference on Games (CoG) 2024 [paper][code] #video-adventure #planning #prompting
[2024/03] Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation (HAS) ICLR 2024 Workshop [paper] #minecraft #planning #multi-agent #vlm
[2024/03] Embodied LLM Agents Learn to Cooperate in Organized Teams IEEE Transactions on Computational Social Systems 2024 [paper] #competition #planning #multi-agent
[2024/03] Will GPT-4 Run DOOM? IEEE Transactions on Games 2024 [paper][code] #action #planning #training
[2024/03] ReAct Meets ActRe: Autonomous Annotation of Agent Trajectories for Contrastive Self-Training COLM [paper] #text-adventure #planning #training #self-improvement
[2024/03] StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows COLM [paper] #text-adventure #planning #self-improvement
[2024/03] AgentKit: Structured LLM Reasoning with Dynamic Graphs COLM [paper] #crafter #planning
[2024/02] Empowering Large Language Model Agents through Action Learning COLM [paper][code] #text-adventure #planning #self-improvement
[2024/02] RL-GPT: Integrating Reinforcement Learning and Code-as-policy NeurIPS 2024 oral [paper] #minecraft #planning #tool-use #training
[2023/12] MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception CVPR 2024 [paper][code] #minecraft #planning #vlm
[2023/12] Creative Agents: Empowering Agents with Imagination for Creative Tasks UAI 2023 [paper][code] #minecraft #planning
[2023/12] Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach NeurIPS 2024 poster [paper][code] #competition #planning
[2023/11] ADaPT: As-Needed Decomposition and Planning with Language Models NAACL 2023 [paper][code] #text-adventure #planning
[2023/11] JARVIS-1: Open-world Multi-task Agents with Memory-Augmented Multimodal Language Models TPAMI 2023 [paper][code] #minecraft #planning #memory
[2023/10] Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models ICML 2024 [paper][code] #text-adventure #planning #training
[2023/10] LLaMA Rider: Spurring Large Language Models to Explore the Open World NAACL 2023 [paper][code] #minecraft #planning #training
[2023/10] Octopus: Embodied Vision-Language Programmer from Environmental Feedback ECCV 2023 [paper][code] #sim-embodied #planning #training #vlm
[2023/10] Evaluating Multi-agent Coordination Abilities in Large Language Models NAACL 2023 [paper] #cooperation #planning #multi-agent #prompting
[2023/10] Theory of Mind for Multi-Agent Collaboration via Large Language Models EMNLP 2023 [paper][code] #cooperation #planning #multi-agent #training
[2023/09] Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4 COLM 2024 [paper] #competition #planning #memory #prompting
[2023/09] MindAgent: Emergent Gaming Interaction NAACL 2023 [paper] #cooperation #planning #multi-agent #prompting
[2023/08] AgentSims: An Open-Source Sandbox for Large Language Model Evaluation arXiv [paper][code] #sim-social #planning #tool-use
[2023/07] Building Cooperative Embodied Agents Modularly with Large Language Models ICLR 2024 [paper][code] #cooperation #planning #multi-agent #training
[2023/05] Language Models Meet World Models: Embodied Experiences Enhance Language Models NeurIPS 2023 [paper][code] #sim-embodied #planning #world-model
[2023/05] SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks NeurIPS 2023 [paper][code] #text-adventure #planning
[2023/03] Plan4MC: Skill Reinforcement Learning and Planning for Open-World Minecraft Tasks FMDM@NeurIPS2023 [paper][code] #minecraft #planning #training
[2023/02] Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents NeurIPS 2023 [paper][code] #minecraft #planning #prompting
[2022/12] LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models ICCV 2023 [paper] #sim-embodied #planning #prompting
[2022/10] ReAct: Synergizing Reasoning and Acting in Language Models ICLR 2023 [paper][code] #text-adventure #planning #training
[2020/10] ALFWorld: Aligning Text and Embodied Environments for Interactive Learning ICLR 2021 [paper][code] #text-adventure #planning

memory

[2026/06] SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training arXiv [paper][code] #text-adventure #memory #training
[2026/06] SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale arXiv [paper] #text-adventure #memory #self-improvement
[2026/05] Belief Memory: Agent Memory Under Partial Observability arXiv [paper] #text-adventure #memory
[2026/05] GASim: A Graph-Accelerated Hybrid Framework for Social Simulation arXiv [paper][code] #sim-social #memory #multi-agent
[2026/05] ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic Profiles arXiv [paper] #sim-social #memory #multi-agent
[2026/05] Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents arXiv [paper] #text-adventure #memory #tool-use
[2026/05] SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs arXiv [paper] #text-adventure #memory #tool-use #training
[2026/05] Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents arXiv [paper] #text-adventure #memory
[2026/05] SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems arXiv [paper] #text-adventure #planning #memory #tool-use
[2026/04] Aligning Progress and Feasibility: A Neuro-Symbolic Dual Memory Framework for Long-Horizon LLM Agents arXiv [paper] #text-adventure #planning #memory
[2026/04] LLM-Agent-based Social Simulation for Attitude Diffusion arXiv [paper] #sim-social #memory
[2026/04] Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows arXiv [paper] #text-adventure #planning #memory #multi-agent
[2026/04] GraSP: Graph-Structured Skill Compositions for LLM Agents arXiv [paper] #text-adventure #planning #memory #self-improvement
[2026/04] Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game arXiv [paper] #minecraft #memory #multi-agent #vlm
[2026/03] RPMS: Enhancing LLM-Based Embodied Planning through Rule-Augmented Memory Synergy arXiv [paper] #text-adventure #planning #memory
[2026/03] RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback arXiv [paper] #text-adventure #memory #training #self-improvement
[2026/03] Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios arXiv [paper] #competition #planning #memory #multi-agent
[2026/02] SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning arXiv [paper][code] #text-adventure #memory #tool-use #training
[2025/12] EZYer: A simulacrum of high school with generative agent arXiv [paper] #sim-social #memory
[2025/12] ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning arXiv [paper] #sim-embodied #planning #memory #training
[2025/12] Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2025 [paper] #text-adventure #memory
[2025/12] ReCollab: Retrieval-Augmented LLMs for Cooperative Ad-hoc Teammate Modeling arXiv [paper] #cooperation #memory
[2025/11] Knowledge Graph-enhanced Large Language Model for Incremental Game PlayTesting IEICE Transactions on Information and Systems 2025 [paper] #minecraft #memory
[2025/10] Fine-tuning with RAG for Improving LLM Learning of New Skills arXiv [paper] #text-adventure #planning #memory #training
[2025/10] Memory-Augmented State Machine Prompting: A Novel LLM Agent Framework for Real-Time Strategy Games arXiv [paper] #competition #memory
[2025/10] Alita-G: Self-Evolving Generative Agent for Agent Generation arXiv [paper] #sim-social #memory #self-improvement
[2025/09] World Model Implanting for Test-time Adaptation of Embodied Agents ICML 2025 poster [paper] #text-adventure #memory #world-model #prompting
[2025/09] Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization ICLR 2026 Poster [paper] #text-adventure #memory #training
[2025/08] Vistawise: Building Cost-effective Agent with Cross-modal Knowledge Graph for Minecraft EMNLP 2025 [paper] #minecraft #memory #tool-use
[2025/08] CHBench: A Cognitive Hierarchy Benchmark for Evaluating Strategic Reasoning Capability of LLMs arXiv [paper] #memory
[2025/06] StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turns arXiv [paper] #text-adventure #memory
[2025/05] Knowledge Retrieval in LLM Gaming: A Shift from Entity-Centric to Goal-Oriented Graphs Knowledge-Based Systems 2025 [paper] #minecraft #planning #memory
[2025/03] Plancraft: an evaluation dataset for planning with LLM agents COLM 2025 [paper] #minecraft #planning #memory #tool-use
[2025/02] LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning arXiv [paper] #crafter #planning #memory #multi-agent
[2024/11] MrSteve: Instruction-Following Agents with What-Where-When Memory ICLR 2025 [paper][code] #minecraft #memory
[2024/09] MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory ICLR 2025 Poster [paper] #minecraft #memory
[2024/08] Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-horizon Tasks NeurIPS 2024 [paper][code] #minecraft #planning #memory #prompting
[2024/07] Arigraph: Learning knowledge graph world models with episodic memory for llm agents IJCAI 2024 [paper] #text-adventure #planning #memory
[2024/05] Agent Planning with World Knowledge Model NeurIPS 2024 [paper][code] #text-adventure #planning #memory #world-model
[2023/11] JARVIS-1: Open-world Multi-task Agents with Memory-Augmented Multimodal Language Models TPAMI 2023 [paper][code] #minecraft #planning #memory
[2023/11] See and Think: Embodied Agent in Virtual Environment ECCV 2023 [paper][code] #minecraft #memory
[2023/10] Lyfe Agents: Generative agents for low-cost real-time social interactions arXiv [paper] #sim-social #memory #multi-agent #self-improvement
[2023/09] Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4 COLM 2024 [paper] #competition #planning #memory #prompting
[2023/09] Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf arXiv [paper] #communication #memory

multi-agent

[2026/06] Can LLM Agents Sustain Long-Horizon Organizational Dynamics? arXiv [paper] #sim-social #planning #multi-agent
[2026/06] Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social Simulation arXiv [paper] #sim-social #multi-agent
[2026/06] SMAC-Talk: A Natural Language Extension of the StarCraft Multi-Agent Challenge for Large Language Models arXiv [paper] #competition #multi-agent
[2026/05] GASim: A Graph-Accelerated Hybrid Framework for Social Simulation arXiv [paper][code] #sim-social #memory #multi-agent
[2026/05] ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic Profiles arXiv [paper] #sim-social #memory #multi-agent
[2026/05] GAMBIT: A Three-Mode Benchmark for Adversarial Robustness in Multi-Agent LLM Collectives arXiv [paper] #competition #multi-agent #prompting
[2026/05] ALSO: Adversarial Online Strategy Optimization for Social Agents arXiv [paper] #sim-social #multi-agent #training
[2026/05] MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs arXiv [paper] #communication #multi-agent
[2026/05] PatchBoard: Schema-Grounded State Mutation for Reliable and Auditable LLM Multi-Agent Collaboration arXiv [paper] #text-adventure #multi-agent
[2026/04] MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2026 [paper] #competition #multi-agent #training
[2026/04] Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows arXiv [paper] #text-adventure #planning #memory #multi-agent
[2026/04] Don't Make the LLM Read the Graph: Make the Graph Think arXiv [paper] #cooperation #multi-agent
[2026/04] Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game arXiv [paper] #minecraft #memory #multi-agent #vlm
[2026/03] How Clued up are LLMs? Evaluating Multi-Step Deductive Reasoning in a Text-Based Game Environment arXiv [paper] #text-adventure #multi-agent #training
[2026/03] GTO Wizard Benchmark arXiv [paper] #competition #planning #multi-agent #prompting
[2026/03] Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios arXiv [paper] #competition #planning #memory #multi-agent
[2026/03] Belief-Driven Multi-Agent Collaboration via Approximate Perfect Bayesian Equilibrium for Social Simulation WWW 2026 [paper][code] #sim-social #multi-agent
[2026/03] Deception and Communication in Autonomous Multi-Agent Systems: An Experimental Study with Among Us Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2026 [paper] #communication #multi-agent
[2026/02] The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies arXiv [paper] #sim-social #multi-agent #self-improvement
[2026/01] When Agents See Humans as the Outgroup: Belief-Dependent Bias in LLM-Powered Agents arXiv [paper] #sim-social #multi-agent
[2026/01] Hidden in Plain Text: Measuring LLM Deception Quality Against Human Baselines Using Social Deduction Games International Conference on Agents 2027 [paper] #communication #multi-agent
[2026/01] MARO: Learning Stronger Reasoning from Social Interaction arXiv [paper] #sim-social #multi-agent
[2025/12] WOLF: Werewolf-based Observations for LLM Deception and Falsehoods arXiv [paper] #communication #multi-agent
[2025/12] Robust Agents in Open-Ended Worlds arXiv [paper] #action #multi-agent #training #generation
[2025/12] Agent-Kernel: A MicroKernel Multi-Agent System Framework for Adaptive Social Simulation Powered by LLMs arXiv [paper] #sim-social #multi-agent
[2025/11] DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration arXiv [paper] #sim-embodied #planning #multi-agent #world-model
[2025/11] Multi-agent Undercover Gaming: Hallucination Removal via Counterfactual Test for Multimodal Reasoning arXiv [paper][code] #communication #multi-agent
[2025/11] MADRA: Multi-Agent Debate for Risk-Aware Embodied Planning arXiv [paper] #sim-embodied #planning #multi-agent #prompting
[2025/10] LLM-Hanabi: Evaluating Multi-Agent Gameplays with Theory-of-Mind and Rationale Inference in Imperfect Information Collaboration Game arXiv [paper] #cooperation #multi-agent
[2025/10] Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategies arXiv [paper] #communication #multi-agent #self-improvement
[2025/10] Social Simulations with Large Language Model Risk Utopian Illusion arXiv [paper] #sim-social #multi-agent
[2025/09] Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent arXiv [paper] #text-adventure #planning #multi-agent #self-improvement
[2025/09] PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments 2025 IEEE Conference on Games (CoG) 2025 [paper] #minecraft #multi-agent #self-improvement
[2025/09] HLSMAC: A New StarCraft Multi-Agent Challenge for High-Level Strategic Decision-Making arXiv [paper] #competition #multi-agent #training
[2025/09] SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning ICLR 2026 Poster [paper] #competition #planning #multi-agent #training
[2025/08] CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks Findings of EMNLP 2025 [paper] #minecraft #planning #multi-agent
[2025/08] A Multi-Agent Pokemon Tournament for Evaluating Strategic Reasoning of Large Language Models arXiv [paper] #action #multi-agent
[2025/08] CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning arXiv [paper] #cooperation #planning #multi-agent #training
[2025/07] LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra arXiv [paper][code] #sim-social #multi-agent #training #role-play
[2025/07] CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language Games ACL 2025 [paper][code] #communication #multi-agent
[2025/06] UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI ICCV 2025 [paper][code] #benchmark #multi-agent #training
[2025/06] IndoorWorld: Integrating Physical Task Solving and Social Simulation in A Heterogeneous Multi-Agent Environment EMNLP 2025 [paper] #sim-social #multi-agent
[2025/06] WereWolf-Plus: An Update of Werewolf Game setting Based on DSGBench arXiv [paper][code] #communication #multi-agent
[2025/06] The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind arXiv [paper] #multi-agent #training
[2025/06] AgentGroupChat-V2: Divide-and-Conquer Is What LLM-Based Multi-Agent System Need arXiv [paper][code] #sim-social #planning #multi-agent
[2025/06] PSALM-V: Automating Symbolic Planning in Interactive Visual Environments with Large Language Models arXiv [paper] #cooperation #planning #multi-agent
[2025/05] Is Your LLM Really Mastering the Concept? A Multi-Agent Benchmark arXiv [paper][code] #benchmark #multi-agent
[2025/04] Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning arXiv [paper][code] #minecraft #multi-agent #training
[2025/04] BookWorld: From Novels to Interactive Agent Societies for Creative Story Generation arXiv [paper] #sim-social #multi-agent #generation
[2025/04] LLM-PySC2: Starcraft II learning environment for Large Language Models NeurIPS 2025 poster [paper] #competition #planning #multi-agent #vlm
[2025/03] Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems arXiv [paper] #minecraft #planning #multi-agent #tool-use
[2025/03] Playing games with Large language models: Randomness and strategy arXiv [paper] #multi-agent
[2025/03] Society of Mind Meets Real-Time Strategy: A Hierarchical Multi-Agent Framework for Strategic Reasoning COLM 2025 [paper] #competition #multi-agent #training
[2025/02] LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning arXiv [paper] #crafter #planning #memory #multi-agent
[2024/12] TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft arXiv [paper][code] #minecraft #multi-agent #training #vlm
[2024/09] Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search ICLR 2025 Poster [paper] #communication #planning #multi-agent #training
[2024/08] Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information 2024 IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) 2024 [paper] #competition #planning #multi-agent #training
[2024/06] VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft Findings of ACL 2024 [paper][code] #minecraft #planning #multi-agent
[2024/06] Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theory arXiv [paper] #sim-social #multi-agent
[2024/06] PLAYER: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games arXiv [paper] #communication #multi-agent
[2024/05] Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration ACL 2024 [paper][code] #cooperation #planning #multi-agent #training
[2024/05] Reflective Multi-Agent Collaboration based on Large Language Models NeurIPS 2024 poster [paper] #competition #planning #multi-agent #training
[2024/05] Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy NeurIPS 2024 poster [paper] #communication #planning #multi-agent #self-improvement
[2024/03] MineLand: Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs arXiv [paper][code] #minecraft #multi-agent #vlm
[2024/03] Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation (HAS) ICLR 2024 Workshop [paper] #minecraft #planning #multi-agent #vlm
[2024/03] Embodied LLM Agents Learn to Cooperate in Organized Teams IEEE Transactions on Computational Social Systems 2024 [paper] #competition #planning #multi-agent
[2024/03] Can LLM-Augmented Autonomous Agents Cooperate?, An Evaluation of Their Cooperative Capabilities through Melting Pot IEEE Transactions on Artificial Intelligence 2024 [paper] #cooperation #multi-agent
[2024/03] Helmsman of the Masses? Evaluate the Opinion Leadership of Large Language Models in the Werewolf Game COLM [paper] #communication #multi-agent
[2023/12] Cooperation on the Fly: Exploring Language Agents for Ad Hoc Teamwork in the Avalon Game arXiv [paper] #communication #multi-agent
[2023/12] Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games ACL 2023 [paper] #communication #multi-agent #prompting
[2023/11] War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars arXiv [paper][code] #communication #multi-agent
[2023/10] Lyfe Agents: Generative agents for low-cost real-time social interactions arXiv [paper] #sim-social #memory #multi-agent #self-improvement
[2023/10] Evaluating Multi-agent Coordination Abilities in Large Language Models NAACL 2023 [paper] #cooperation #planning #multi-agent #prompting
[2023/10] Theory of Mind for Multi-Agent Collaboration via Large Language Models EMNLP 2023 [paper][code] #cooperation #planning #multi-agent #training
[2023/10] LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay EMNLP 2023 [paper] #communication #multi-agent
[2023/10] Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models arXiv [paper][code] #communication #multi-agent
[2023/09] MindAgent: Emergent Gaming Interaction NAACL 2023 [paper] #cooperation #planning #multi-agent #prompting
[2023/07] Building Cooperative Embodied Agents Modularly with Large Language Models ICLR 2024 [paper][code] #cooperation #planning #multi-agent #training

world-model

[2026/05] PriorZero: Bridging Language Priors and World Models for Decision Making arXiv [paper][code] #text-adventure #planning #world-model #training
[2026/02] World Models for Policy Refinement in StarCraft II arXiv [paper] #competition #world-model #prompting
[2026/02] CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent Pipelines arXiv [paper] #text-adventure #planning #world-model #training
[2026/02] Reinforcement World Model Learning for LLM-based Agents arXiv [paper] #text-adventure #world-model
[2025/11] DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration arXiv [paper] #sim-embodied #planning #multi-agent #world-model
[2025/09] World Model Implanting for Test-time Adaptation of Embodied Agents ICML 2025 poster [paper] #text-adventure #memory #world-model #prompting
[2025/09] DreamPhase: Offline Imagination and Uncertainty-Guided Planning for Large-Language-Model Agents ICLR 2026 Poster [paper] #text-adventure #planning #world-model
[2025/07] CoEx -- Co-evolving World-model and Exploration EMNLP 2025 [paper] #text-adventure #planning #world-model
[2025/06] Improving LLM Agent Planning with In-Context Learning via Atomic Fact Augmentation and Lookahead Search arXiv [paper] #text-adventure #planning #world-model #training
[2025/05] PoE-World: Compositional World Modeling with Products of Programmatic Experts NeurIPS 2025 spotlight [paper] #action #planning #world-model
[2025/05] WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents NeurIPS 2025 poster [paper] #minecraft #planning #world-model #prompting
[2025/04] WALL-E 2.0: World Alignment by NeuroSymbolic Learning Improves World Model-based LLM Agents arXiv [paper][code] #minecraft #planning #world-model #prompting
[2025/04] Better Decisions through the Right Causal World Model arXiv [paper] #action #planning #world-model #training
[2025/02] Optimus-2: Multimodal World Model for Open-World Minecraft Agents CVPR 2025 [paper][code] #minecraft #planning #world-model #vlm
[2024/10] WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents arXiv [paper][code] #minecraft #planning #world-model
[2024/05] Agent Planning with World Knowledge Model NeurIPS 2024 [paper][code] #text-adventure #planning #memory #world-model
[2023/05] Language Models Meet World Models: Embodied Experiences Enhance Language Models NeurIPS 2023 [paper][code] #sim-embodied #planning #world-model
[2023/04] Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions arXiv [paper] #text-adventure #world-model

tool-use

[2026/05] Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning arXiv [paper] #text-adventure #tool-use #training
[2026/05] Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents arXiv [paper] #text-adventure #memory #tool-use
[2026/05] PokerSkill: LLMs Can Play Expert-Level Poker without Training or Solvers arXiv [paper][code] #competition #tool-use #prompting
[2026/05] SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs arXiv [paper] #text-adventure #memory #tool-use #training
[2026/05] SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems arXiv [paper] #text-adventure #planning #memory #tool-use
[2026/04] Nemobot Games: Crafting Strategic AI Gaming Agents for Interactive Learning with Large Language Models arXiv [paper] #tool-use #training #self-improvement
[2026/02] SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning arXiv [paper][code] #text-adventure #memory #tool-use #training
[2025/09] Speculative Actions: A Lossless Framework for Faster AI Agents ICLR 2026 Oral [paper] #competition #tool-use
[2025/09] Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning ICLR 2026 Poster [paper] #text-adventure #tool-use #training
[2025/08] Vistawise: Building Cost-effective Agent with Cross-modal Knowledge Graph for Minecraft EMNLP 2025 [paper] #minecraft #memory #tool-use
[2025/05] Agent-Environment Alignment via Automated Interface Generation arXiv [paper][code] #text-adventure #tool-use
[2025/05] Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL NeurIPS 2025 poster [paper] #communication #planning #tool-use #training
[2025/03] Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems arXiv [paper] #minecraft #planning #multi-agent #tool-use
[2025/03] Plancraft: an evaluation dataset for planning with LLM agents COLM 2025 [paper] #minecraft #planning #memory #tool-use
[2024/07] AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents ACL 2024 [paper][code] #text-adventure #tool-use
[2024/07] Odyssey: Empowering Agents with Open-World Skills. IJCAI 2024 [paper][code] #minecraft #planning #tool-use
[2024/04] Learning From Failure: Integrating Negative Examples When Fine-tuning Large Language Models as Agent arXiv [paper][code] #text-adventure #tool-use #training
[2024/02] RL-GPT: Integrating Reinforcement Learning and Code-as-policy NeurIPS 2024 oral [paper] #minecraft #planning #tool-use #training
[2023/08] AgentSims: An Open-Source Sandbox for Large Language Model Evaluation arXiv [paper][code] #sim-social #planning #tool-use
[2023/05] VOYAGER: An Open-Ended Embodied Agent with Large Language Models FMDM@NeurIPS2023 [paper][code] #minecraft #tool-use #training

training

[2026/06] SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training arXiv [paper][code] #text-adventure #memory #training
[2026/06] Cross-Environment Neural Reranking for Sample-Efficient Action Selection in Text-Based Agents arXiv [paper] #text-adventure #training
[2026/06] When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training arXiv [paper] #text-adventure #training
[2026/05] Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning arXiv [paper] #action #training #vlm
[2026/05] T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning arXiv [paper][code] #text-adventure #training
[2026/05] ANO: A Principled Approach to Robust Policy Optimization arXiv [paper] #action #training
[2026/05] From History to State: Constant-Context Skill Learning for LLM Agents arXiv [paper] #text-adventure #planning #training
[2026/05] StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction arXiv [paper] #text-adventure #training
[2026/05] AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning arXiv [paper] #text-adventure #training
[2026/05] Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents arXiv [paper] #text-adventure #training #self-improvement
[2026/05] Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning arXiv [paper] #text-adventure #tool-use #training
[2026/05] SkillMaster: Toward Autonomous Skill Mastery in LLM Agents arXiv [paper] #text-adventure #training
[2026/05] Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty arXiv [paper] #sim-embodied #training
[2026/05] PriorZero: Bridging Language Priors and World Models for Decision Making arXiv [paper][code] #text-adventure #planning #world-model #training
[2026/05] Generalization or Memorization? Brittleness Testing for Chess-Trained Language Models arXiv [paper] #competition #training
[2026/05] ALSO: Adversarial Online Strategy Optimization for Social Agents arXiv [paper] #sim-social #multi-agent #training
[2026/05] Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay arXiv [paper] #action #planning #training #vlm
[2026/05] What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents arXiv [paper] #text-adventure #training
[2026/05] GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents arXiv [paper] #minecraft #training #vlm
[2026/05] SKILLC: Learning Autonomous Skill Internalization in LLM Agents via Contrastive Credit Assignment arXiv [paper] #text-adventure #training
[2026/05] SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs arXiv [paper] #text-adventure #memory #tool-use #training
[2026/05] Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning arXiv [paper] #text-adventure #training
[2026/05] Playing with Words, Improving with Rewards: Training Language Models for Creative Association arXiv [paper] #communication #training
[2026/05] Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL arXiv [paper][code] #text-adventure #training
[2026/05] R2V Agent: Teaching SLMs When to Ask for Help arXiv [paper] #text-adventure #training
[2026/04] MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2026 [paper] #competition #multi-agent #training
[2026/04] Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents arXiv [paper][code] #text-adventure #training
[2026/04] GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning arXiv [paper] #action #training
[2026/04] Nemobot Games: Crafting Strategic AI Gaming Agents for Interactive Learning with Large Language Models arXiv [paper] #tool-use #training #self-improvement
[2026/04] DPEPO: Diverse Parallel Exploration Policy Optimization for LLM-based Agents arXiv [paper][code] #text-adventure #training
[2026/03] On the Strengths and Weaknesses of Data for Open-set Embodied Assistance arXiv [paper] #cooperation #training
[2026/03] Hindsight Credit Assignment for Long-Horizon LLM Agents arXiv [paper] #text-adventure #training
[2026/03] How Clued up are LLMs? Evaluating Multi-Step Deductive Reasoning in a Text-Based Game Environment arXiv [paper] #text-adventure #multi-agent #training
[2026/03] PolicySim: An LLM-Based Agent Social Simulation Sandbox for Proactive Policy Optimization WWW 2026 [paper] #sim-social #training
[2026/03] Grounded Chess Reasoning in Language Models via Master Distillation arXiv [paper] #competition #planning #training
[2026/03] RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback arXiv [paper] #text-adventure #memory #training #self-improvement
[2026/02] VLM-Guided Experience Replay arXiv [paper] #planning #training #vlm
[2026/02] Implicit Strategic Optimization: Rethinking Long-Horizon Decision-Making in Adversarial Poker Environments arXiv [paper] #action #training
[2026/02] Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents arXiv [paper] #text-adventure #planning #training
[2026/02] VAM: Verbalized Action Masking for Controllable Exploration in RL Post-Training -- A Chess Case Study arXiv [paper] #competition #training
[2026/02] CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent Pipelines arXiv [paper] #text-adventure #planning #world-model #training
[2026/02] SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards arXiv [paper] #text-adventure #training
[2026/02] SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning arXiv [paper][code] #text-adventure #memory #tool-use #training
[2026/01] NitroGen: An Open Foundation Model for Generalist Gaming Agents arXiv [paper] #benchmark #training
[2026/01] Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents arXiv [paper] #text-adventure #planning #training
[2026/01] Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates arXiv [paper][code] #text-adventure #training
[2026/01] HumanLLM: Towards Personalized Understanding and Simulation of Human Nature arXiv [paper] #sim-social #training
[2025/12] Synergizing Code Coverage and Gameplay Intent: Coverage-Aware Game Playtesting with LLM-Guided Reinforcement Learning arXiv [paper] #minecraft #training
[2025/12] ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning arXiv [paper] #sim-embodied #planning #memory #training
[2025/12] Measuring Fine-Grained Negotiation Tactics of Humans and LLMs in Diplomacy arXiv [paper] #communication #training
[2025/12] Robust Agents in Open-Ended Worlds arXiv [paper] #action #multi-agent #training #generation
[2025/10] Fine-tuning with RAG for Improving LLM Learning of New Skills arXiv [paper] #text-adventure #planning #memory #training
[2025/10] Graph-Enhanced Policy Optimization in LLM Agent Training arXiv [paper] #text-adventure #planning #training
[2025/10] SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph arXiv [paper] #text-adventure #training
[2025/09] HLSMAC: A New StarCraft Multi-Agent Challenge for High-Level Strategic Decision-Making arXiv [paper] #competition #multi-agent #training
[2025/09] Exploration with Foundation Models: Capabilities, Limitations, and Hybrid Approaches arXiv [paper] #action #training #vlm
[2025/09] Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents arXiv [paper] #text-adventure #training
[2025/09] Goal-Guided Efficient Exploration via Large Language Model in Reinforcement Learning arXiv [paper] #crafter #planning #training
[2025/09] Reward Is Enough: LLMs Are In-Context Reinforcement Learners ICLR 2026 Poster [paper] #text-adventure #training #self-improvement
[2025/09] Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations ICLR 2026 Poster [paper] #text-adventure #training
[2025/09] SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning ICLR 2026 Poster [paper] #competition #planning #multi-agent #training
[2025/09] Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization ICLR 2026 Poster [paper] #text-adventure #memory #training
[2025/09] Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning ICLR 2026 Poster [paper] #text-adventure #tool-use #training
[2025/08] Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2025 [paper] #text-adventure #planning #training #vlm
[2025/08] Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy AAAI 2025 [paper] #communication #training
[2025/08] CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning arXiv [paper] #cooperation #planning #multi-agent #training
[2025/08] Learning Game-Playing Agents with Generative Code Optimization arXiv [paper] #action #training #self-improvement
[2025/08] SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making Tasks arXiv [paper] #competition #planning #training #self-improvement
[2025/08] HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents arXiv [paper] #crafter #planning #training
[2025/07] LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra arXiv [paper][code] #sim-social #multi-agent #training #role-play
[2025/06] Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games arXiv [paper][code] #benchmark #training
[2025/06] UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI ICCV 2025 [paper][code] #benchmark #multi-agent #training
[2025/06] Empowering Economic Simulation for Massively Multiplayer Online Games through Generative Agent-Based Modeling KDD 2025 [paper] #sim-social #training
[2025/06] Enhancing Decision-Making of Large Language Models via Actor-Critic ICML 2025 poster [paper] #text-adventure #training
[2025/06] Improving LLM Agent Planning with In-Context Learning via Atomic Fact Augmentation and Lookahead Search arXiv [paper] #text-adventure #planning #world-model #training
[2025/06] DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy ICML 2025 poster [paper] #communication #training
[2025/06] OmniReflect: Discovering Transferable Constitutions for LLM agents via Neuro-Symbolic Reflections arXiv [paper] #text-adventure #planning #training #self-improvement
[2025/06] The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind arXiv [paper] #multi-agent #training
[2025/06] GuessBench: Sensemaking Multimodal Creativity in the Wild arXiv [paper] #minecraft #training #vlm
[2025/06] KnowMap: Efficient Knowledge-Driven Task Adaptation for LLMs arXiv [paper] #text-adventure #training
[2025/05] lmgame-Bench: How Good are LLMs at Playing Games?." ICLR 2026 Poster [paper][code] #benchmark #planning #training
[2025/05] Frog Soup: Zero-Shot, In-Context, and Sample-Efficient Frogger Agents arXiv [paper][code] #action #training
[2025/05] Enfoque Odychess: Un método dialéctico, constructivista y adaptativo para la enseñanza del ajedrez con inteligencias artificiales generativas arXiv [paper] #competition #training
[2025/05] Multiple Weaks Win Single Strong: Large Language Models Ensemble Weak Reinforcement Learning Agents into a Supreme One arXiv [paper] #action #training
[2025/05] Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning ICML 2025 poster [paper] #text-adventure #planning #training
[2025/05] Retrospex: Language Agent Meets Offline Reinforcement Learning Critic EMNLP 2025 [paper] #text-adventure #training
[2025/05] SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution arXiv [paper][code] #text-adventure #training
[2025/05] Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs NeurIPS 2025 poster [paper] #action #training
[2025/05] Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL NeurIPS 2025 poster [paper] #communication #planning #tool-use #training
[2025/05] Can Large Language Models Master Complex Card Games? NeurIPS 2025 poster [paper][code] #competition #training
[2025/05] MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning NeurIPS 2025 poster [paper] #minecraft #training
[2025/05] SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents NeurIPS 2025 poster [paper] #text-adventure #planning #training #self-improvement
[2025/05] LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models NeurIPS 2025 spotlight [paper][code] #action #training
[2025/04] Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning arXiv [paper][code] #minecraft #multi-agent #training
[2025/04] Better Decisions through the Right Causal World Model arXiv [paper] #action #planning #world-model #training
[2025/04] Enhancing Player Enjoyment with a Two-Tier DRL and LLM-Based Agent System for Fighting Games arXiv [paper] #training
[2025/04] Monte Carlo Planning with Large Language Model for Text-Based Game Agents ICLR 2025 Poster [paper] #text-adventure #planning #training
[2025/04] MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework NeurIPS 2025 poster [paper] #sim-social #planning #training
[2025/04] Group-in-Group Policy Optimization for LLM Agent Training NeurIPS 2025 poster [paper] #text-adventure #training
[2025/03] GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks CVPR 2025 [paper] #text-adventure #planning #training #vlm
[2025/03] Society of Mind Meets Real-Time Strategy: A Hierarchical Multi-Agent Framework for Strategic Reasoning COLM 2025 [paper] #competition #multi-agent #training
[2025/02] Process Reward Models for LLM Agents: Practical Framework and Directions arXiv [paper][code] #text-adventure #training
[2025/01] POKERBENCH: Training Large Language Models to become Professional Poker Players AAAI 2025 [paper] #competition #planning #training
[2025/01] DVM: Towards Controllable LLM Agents in Social Deduction Games IEEE International Conference on Acoustics, Speech, and Signal Processing 2025 [paper] #communication #training
[2025/01] Complete Chess Games Enable LLM Become A Chess Master NAACL 2025 [paper] #competition #training
[2025/01] LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations ICML 2025 poster [paper] #action #planning #training
[2025/01] Language Models as Implicit Tree Search ICML 2025 poster [paper] #competition #planning #training
[2025/01] LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence ICML 2025 poster [paper] #minecraft #training
[2024/12] TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft arXiv [paper][code] #minecraft #multi-agent #training #vlm
[2024/12] Fine-tuning large vision-language models as decision-making agents via reinforcement learning NeurIPS 2024 [paper][code] #text-adventure #training #vlm
[2024/09] Can VLMs Play Action Role-Playing Games? Take Black Myth Wukong as a Study Case arXiv [paper][code] #action #planning #training
[2024/09] Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search ICLR 2025 Poster [paper] #communication #planning #multi-agent #training
[2024/09] MaestroMotif: Skill Design from Artificial Intelligence Feedback ICLR 2025 Oral [paper] #action #training
[2024/09] Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems ICLR 2025 Poster [paper] #sim-embodied #training
[2024/09] Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback ICLR 2025 Poster [paper] #text-adventure #planning #training #self-improvement
[2024/09] BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games ICLR 2025 Poster [paper] #action #planning #training #vlm
[2024/08] Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information 2024 IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) 2024 [paper] #competition #planning #multi-agent #training
[2024/08] Atari-GPT: Investigating the Capabilities of Multimodal Large Language Models as Low-Level Policies for Atari Games arXiv [paper] #action #planning #training
[2024/07] OmniJARVIS: Omni-Modal Open-World Agents in Minecraft NeurIPS 2024 [paper][code] #minecraft #training #vlm
[2024/06] STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models ACL 2024 [paper][code] #text-adventure #training
[2024/05] Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration ACL 2024 [paper][code] #cooperation #planning #multi-agent #training
[2024/05] Policy Improvement using Language Feedback Models NeurIPS 2024 poster [paper] #text-adventure #training
[2024/05] Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf NeurIPS 2024 poster [paper] #communication #training
[2024/05] Reflective Multi-Agent Collaboration based on Large Language Models NeurIPS 2024 poster [paper] #competition #planning #multi-agent #training
[2024/04] Learning From Failure: Integrating Negative Examples When Fine-tuning Large Language Models as Agent arXiv [paper][code] #text-adventure #tool-use #training
[2024/04] ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy arXiv [paper] #text-adventure #planning #training #self-improvement
[2024/04] World Models with Hints of Large Language Models for Goal Achieving NAACL 2024 [paper] #crafter #training #vlm
[2024/04] Self-playing Adversarial Language Game Enhances LLM Reasoning NeurIPS 2024 [paper][code] #communication #training #self-improvement
[2024/03] Language Guided Exploration for RL Agents in Text Environments NAACL 2024 [paper][code] #text-adventure #training
[2024/03] Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents ACL 2024 [paper][code] #text-adventure #training #self-improvement
[2024/03] EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents COLM [paper] #crafter #training
[2024/03] SOTOPIA-$\pi$: Interactive Learning of Socially Intelligent Language Agents ACL 2024 [paper][code] #sim-social #training
[2024/03] Will GPT-4 Run DOOM? IEEE Transactions on Games 2024 [paper][code] #action #planning #training
[2024/03] O3D: Offline Data-driven Discovery and Distillation for Sequential Decision-Making with Large Language Models COLM [paper] #text-adventure #training
[2024/03] ReAct Meets ActRe: Autonomous Annotation of Agent Trajectories for Contrastive Self-Training COLM [paper] #text-adventure #planning #training #self-improvement
[2024/02] RL-GPT: Integrating Reinforcement Learning and Code-as-policy NeurIPS 2024 oral [paper] #minecraft #planning #tool-use #training
[2024/02] PokéLLMon: A Human-Parity Agent for Pokémon Battles with Large Language Models TOIT 2025 [paper][code] #competition #training
[2024/02] Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization ACL 2024 [paper][code] #competition #training
[2024/02] Enhance Reasoning for Large Language Models in the Game Werewolf arXiv [paper] #communication #training
[2024/01] True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning arXiv [paper][code] #sim-embodied #training
[2024/01] PokerGPT: An End-to-End Lightweight Solver for Multi-Player Texas Hold'em via Large Language Model arXiv [paper] #competition #training
[2024/01] SwarmBrain: Embodied agent for real-time strategy game StarCraft II via large language models arXiv [paper] #competition #training
[2023/12] Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft CVPR 2023 [paper] #minecraft #training
[2023/10] FireAct: Toward Language Agent Fine-tuning arXiv [paper][code] #text-adventure #training
[2023/10] Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models ICML 2024 [paper][code] #text-adventure #planning #training
[2023/10] LLaMA Rider: Spurring Large Language Models to Explore the Open World NAACL 2023 [paper][code] #minecraft #planning #training
[2023/10] Octopus: Embodied Vision-Language Programmer from Environmental Feedback ECCV 2023 [paper][code] #sim-embodied #planning #training #vlm
[2023/10] Theory of Mind for Multi-Agent Collaboration via Large Language Models EMNLP 2023 [paper][code] #cooperation #planning #multi-agent #training
[2023/10] Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game ICML 2023 [paper] #communication #training
[2023/10] Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation arXiv [paper] #communication #training
[2023/09] Motif: Intrinsic Motivation from Artificial Intelligence Feedback ICLR 2024 [paper][code] #video-adventure #training
[2023/09] AdaRefiner: Refining Decisions of Language Models with Adaptive Feedback NAACL 2023 [paper] #crafter #training
[2023/07] Building Cooperative Embodied Agents Modularly with Large Language Models ICLR 2024 [paper][code] #cooperation #planning #multi-agent #training
[2023/05] Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory arXiv [paper] #minecraft #training
[2023/05] VOYAGER: An Open-Ended Embodied Agent with Large Language Models FMDM@NeurIPS2023 [paper][code] #minecraft #tool-use #training
[2023/03] Plan4MC: Skill Reinforcement Learning and Planning for Open-World Minecraft Tasks FMDM@NeurIPS2023 [paper][code] #minecraft #planning #training
[2023/03] Reflexion: Language Agents with Verbal Reinforcement Learning NeurIPS 2023 [paper][code] #text-adventure #training #self-improvement
[2023/02] Guiding Pretraining in Reinforcement Learning with Large Language Models ICML 2023 [paper] #crafter #training
[2023/02] Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning ICML 2023 [paper][code] #action #training
[2022/10] ReAct: Synergizing Reasoning and Acting in Language Models ICLR 2023 [paper][code] #text-adventure #planning #training

self-improvement

[2026/06] SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale arXiv [paper] #text-adventure #memory #self-improvement
[2026/05] Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents arXiv [paper] #text-adventure #training #self-improvement
[2026/05] APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents arXiv [paper] #text-adventure #planning #self-improvement
[2026/05] Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM Agents arXiv [paper] #minecraft #self-improvement
[2026/04] Nemobot Games: Crafting Strategic AI Gaming Agents for Interactive Learning with Large Language Models arXiv [paper] #tool-use #training #self-improvement
[2026/04] GraSP: Graph-Structured Skill Compositions for LLM Agents arXiv [paper] #text-adventure #planning #memory #self-improvement
[2026/03] RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback arXiv [paper] #text-adventure #memory #training #self-improvement
[2026/02] MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents arXiv [paper] #text-adventure #self-improvement
[2026/02] The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies arXiv [paper] #sim-social #multi-agent #self-improvement
[2025/10] Alita-G: Self-Evolving Generative Agent for Agent Generation arXiv [paper] #sim-social #memory #self-improvement
[2025/10] Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategies arXiv [paper] #communication #multi-agent #self-improvement
[2025/09] Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent arXiv [paper] #text-adventure #planning #multi-agent #self-improvement
[2025/09] PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments 2025 IEEE Conference on Games (CoG) 2025 [paper] #minecraft #multi-agent #self-improvement
[2025/09] Code Driven Planning with Domain-Adaptive Critic arXiv [paper] #text-adventure #planning #self-improvement
[2025/09] Reward Is Enough: LLMs Are In-Context Reinforcement Learners ICLR 2026 Poster [paper] #text-adventure #training #self-improvement
[2025/08] Learning Game-Playing Agents with Generative Code Optimization arXiv [paper] #action #training #self-improvement
[2025/08] SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making Tasks arXiv [paper] #competition #planning #training #self-improvement
[2025/06] Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback arXiv [paper] #crafter #self-improvement
[2025/06] OmniReflect: Discovering Transferable Constitutions for LLM agents via Neuro-Symbolic Reflections arXiv [paper] #text-adventure #planning #training #self-improvement
[2025/05] SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents NeurIPS 2025 poster [paper] #text-adventure #planning #training #self-improvement
[2025/02] TextGames: Learning to Self-Play Text-Based Puzzle Games via Language Model Reasoning. arXiv [paper] #text-adventure #self-improvement
[2024/12] Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy NeurIPS 2024 [paper][code] #communication #self-improvement
[2024/09] Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback ICLR 2025 Poster [paper] #text-adventure #planning #training #self-improvement
[2024/06] Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement EMNLP 2024 [paper][code] #text-adventure #self-improvement
[2024/05] Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy NeurIPS 2024 poster [paper] #communication #planning #multi-agent #self-improvement
[2024/04] ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy arXiv [paper] #text-adventure #planning #training #self-improvement
[2024/04] Self-playing Adversarial Language Game Enhances LLM Reasoning NeurIPS 2024 [paper][code] #communication #training #self-improvement
[2024/03] Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents ACL 2024 [paper][code] #text-adventure #training #self-improvement
[2024/03] ReAct Meets ActRe: Autonomous Annotation of Agent Trajectories for Contrastive Self-Training COLM [paper] #text-adventure #planning #training #self-improvement
[2024/03] StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows COLM [paper] #text-adventure #planning #self-improvement
[2024/02] Soft Self-Consistency Improves Language Model Agents arXiv [paper][code] #text-adventure #self-improvement
[2024/02] Empowering Large Language Model Agents through Action Learning COLM [paper][code] #text-adventure #planning #self-improvement
[2023/10] Lyfe Agents: Generative agents for low-cost real-time social interactions arXiv [paper] #sim-social #memory #multi-agent #self-improvement
[2023/03] Reflexion: Language Agents with Verbal Reinforcement Learning NeurIPS 2023 [paper][code] #text-adventure #training #self-improvement

prompting

[2026/05] GAMBIT: A Three-Mode Benchmark for Adversarial Robustness in Multi-Agent LLM Collectives arXiv [paper] #competition #multi-agent #prompting
[2026/05] PokerSkill: LLMs Can Play Expert-Level Poker without Training or Solvers arXiv [paper][code] #competition #tool-use #prompting
[2026/04] DORA Explorer: Improving the Exploration Ability of LLMs Without Training arXiv [paper] #text-adventure #planning #prompting
[2026/03] GTO Wizard Benchmark arXiv [paper] #competition #planning #multi-agent #prompting
[2026/03] Reward Prediction with Factorized World States arXiv [paper] #text-adventure #planning #prompting
[2026/02] World Models for Policy Refinement in StarCraft II arXiv [paper] #competition #world-model #prompting
[2026/02] **To Move or Not to Move: Constraint-based Pla

Truncated — view the full README on GitHub.

computer-games

game-agent

large-language-models

llm-based-agent

survey

Contributors

155 commits

3 commits

2 commits

1 commits

Similar repos

zjunlp/LLMAgentPapers

Must-read Papers on LLM Agents.

3,121

AGI-Edgerunners/LLM-Agents-Papers

A repo lists papers related to LLM based agent

2,347

Andrewzh112/Awesome-LLM-based-MultiAgents

js-lee-AI/awesome-llm-agent-papers

A curated, continuously updated reading list of 200+ papers on LLM agents: planning, memory, tool…

WooooDyy/LLM-Agent-Paper-List

The paper list of the 86-page SCIS cover paper "The Rise and Potential of Large Language Model…

8,220

taichengguo/LLM_MultiAgents_Survey_Papers

Large Language Model based Multi-Agents: A Survey of Progress and Challenges (In IJCAI 2024)

1,319

hyp1231/awesome-llm-powered-agent

Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...

2,256

YsTvT/Awesome-Agentic-RL-Papers

107

git-disl/awesome-LLM-game-agent-papers

A Survey on Large Language Model-Based Game Agents (ACM CSUR)

965

169 commits

updated Jun 7, 2026

arxiv.org/pdf/2404.02039.pdf

See the code

README

A Survey on Large Language Model-Based Game Agents (ACM CSUR)

Stars Forks

🔥 Must-read papers for LLM-based Game agents.

📘 Our survey has been accepted by ACM Computing Surveys (CSUR). We are preparing the camera ready. Feel free to reach out if you find missing reference.

💫 We continuously update the GitHub list on a weekly basis.

📝 If you discover any papers that are suitable but not yet included, please open an issue or submit a pull request.

Browse by Genre

#minecraft (60)
#text-adventure (135)
#communication (47)
#competition (51)
#cooperation (15)
#sim-social (56)
#sim-embodied (17)
#sim-other (1)
#crafter (14)
#action (29)
#video-adventure (3)
#benchmark (6)
#other (20)

Browse by Mechanism

#planning (145)
#memory (44)
#multi-agent (78)
#world-model (18)
#tool-use (20)
#training (160)
#self-improvement (34)
#prompting (28)
#role-play (9)
#vlm (37)
#generation (11)

By Genre

minecraft

[2026/05] GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents arXiv [paper] #minecraft #training #vlm
[2026/05] Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM Agents arXiv [paper] #minecraft #self-improvement
[2026/04] Experience Transfer for Multimodal LLM Agents in Minecraft Game arXiv [paper] #minecraft
[2026/04] Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game arXiv [paper] #minecraft #memory #multi-agent #vlm
[2026/03] BLOCK: An Open-Source Bi-Stage MLLM Character-to-Skin Pipeline for Minecraft arXiv [paper] #minecraft #vlm
[2026/02] Requesting Expert Reasoning: Augmenting LLM Agents with Learned Collaborative Intervention arXiv [paper] #minecraft
[2026/01] MineNPC-Task: Task Suite for Memory-Aware Minecraft Agents arXiv [paper] #minecraft
[2025/12] Synergizing Code Coverage and Gameplay Intent: Coverage-Aware Game Playtesting with LLM-Guided Reinforcement Learning arXiv [paper] #minecraft #training
[2025/11] Knowledge Graph-enhanced Large Language Model for Incremental Game PlayTesting IEICE Transactions on Information and Systems 2025 [paper] #minecraft #memory
[2025/09] PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments 2025 IEEE Conference on Games (CoG) 2025 [paper] #minecraft #multi-agent #self-improvement
[2025/09] Experience-based Knowledge Correction for Robust Planning in Minecraft ICLR 2026 Poster [paper] #minecraft #planning
[2025/08] CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks Findings of EMNLP 2025 [paper] #minecraft #planning #multi-agent
[2025/08] Vistawise: Building Cost-effective Agent with Cross-modal Knowledge Graph for Minecraft EMNLP 2025 [paper] #minecraft #memory #tool-use
[2025/07] VoyagerVision: Investigating the Role of Multi-modal Information for Open-ended Learning Systems arXiv [paper] #minecraft #vlm
[2025/07] Referential ambiguity and clarification requests: comparing human and LLM behaviour Proceedings of the Eighth Workshop on Computational Models of Reference, Anaphora and Coreference 2025 [paper] #minecraft
[2025/06] Optimus-3: Towards Generalist Multimodal Minecraft Agents with Scalable Task Experts arXiv [paper][code] #minecraft #planning
[2025/06] Matrix-Game: Interactive World Foundation Model arXiv [paper][code] #minecraft
[2025/06] GuessBench: Sensemaking Multimodal Creativity in the Wild arXiv [paper] #minecraft #training #vlm
[2025/05] Don’t Just Follow MLLM Plans: Robust and Efficient Planning for Open-World Agents arXiv [paper] #minecraft #planning #vlm
[2025/05] Knowledge Retrieval in LLM Gaming: A Shift from Entity-Centric to Goal-Oriented Graphs Knowledge-Based Systems 2025 [paper] #minecraft #planning #memory
[2025/05] BeliefNest: A Joint Action Simulator for Embodied Agents with Theory of Mind arXiv [paper] #minecraft
[2025/05] MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning NeurIPS 2025 poster [paper] #minecraft #training
[2025/05] WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents NeurIPS 2025 poster [paper] #minecraft #planning #world-model #prompting
[2025/04] Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning arXiv [paper][code] #minecraft #multi-agent #training
[2025/04] WALL-E 2.0: World Alignment by NeuroSymbolic Learning Improves World Model-based LLM Agents arXiv [paper][code] #minecraft #planning #world-model #prompting
[2025/03] Uncertainty in Action: Confidence Elicitation in Embodied Agents arXiv [paper] #minecraft
[2025/03] Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems arXiv [paper] #minecraft #planning #multi-agent #tool-use
[2025/03] NeSyC: A Neuro-symbolic Continual Learner For Complex Embodied Tasks In Open Domains ICLR 2025 Poster [paper] #minecraft
[2025/03] Word2Minecraft: Generating 3D Game Levels through Large Language Models arXiv [paper][code] #minecraft #generation
[2025/03] Plancraft: an evaluation dataset for planning with LLM agents COLM 2025 [paper] #minecraft #planning #memory #tool-use
[2025/02] GATE: Graph-based Adaptive Tool Evolution Across Diverse Tasks arXiv [paper][code] #minecraft
[2025/02] Optimus-2: Multimodal World Model for Open-World Minecraft Agents CVPR 2025 [paper][code] #minecraft #planning #world-model #vlm
[2025/01] LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence ICML 2025 poster [paper] #minecraft #training
[2024/12] TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft arXiv [paper][code] #minecraft #multi-agent #training #vlm
[2024/11] MrSteve: Instruction-Following Agents with What-Where-When Memory ICLR 2025 [paper][code] #minecraft #memory
[2024/10] WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents arXiv [paper][code] #minecraft #planning #world-model
[2024/10] ADAM: An Embodied Causal Agent in Open-World Environments ICLR 2025 [paper][code] #minecraft #planning
[2024/09] MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory ICLR 2025 Poster [paper] #minecraft #memory
[2024/08] Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-horizon Tasks NeurIPS 2024 [paper][code] #minecraft #planning #memory #prompting
[2024/07] Odyssey: Empowering Agents with Open-World Skills. IJCAI 2024 [paper][code] #minecraft #planning #tool-use
[2024/07] OmniJARVIS: Omni-Modal Open-World Agents in Minecraft NeurIPS 2024 [paper][code] #minecraft #training #vlm
[2024/06] VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft Findings of ACL 2024 [paper][code] #minecraft #planning #multi-agent
[2024/03] MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control arXiv [paper][code] #minecraft
[2024/03] MineLand: Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs arXiv [paper][code] #minecraft #multi-agent #vlm
[2024/03] Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation (HAS) ICLR 2024 Workshop [paper] #minecraft #planning #multi-agent #vlm
[2024/02] RL-GPT: Integrating Reinforcement Learning and Code-as-policy NeurIPS 2024 oral [paper] #minecraft #planning #tool-use #training
[2024/01] ReGAL: Refactoring Programs to Discover Generalizable Abstractions ICML 2024 [paper][code] #minecraft
[2023/12] MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception CVPR 2024 [paper][code] #minecraft #planning #vlm
[2023/12] Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft CVPR 2023 [paper] #minecraft #training
[2023/12] Creative Agents: Empowering Agents with Imagination for Creative Tasks UAI 2023 [paper][code] #minecraft #planning
[2023/11] JARVIS-1: Open-world Multi-task Agents with Memory-Augmented Multimodal Language Models TPAMI 2023 [paper][code] #minecraft #planning #memory
[2023/11] See and Think: Embodied Agent in Virtual Environment ECCV 2023 [paper][code] #minecraft #memory
[2023/10] LLaMA Rider: Spurring Large Language Models to Explore the Open World NAACL 2023 [paper][code] #minecraft #planning #training
[2023/10] MCU: A Task-centric Framework for Open-ended Agent Evaluation in Minecraft ICML 2023 [paper][code] #minecraft
[2023/10] Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds ICLR 2024 [paper] #minecraft #vlm
[2023/05] Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory arXiv [paper] #minecraft #training
[2023/05] VOYAGER: An Open-Ended Embodied Agent with Large Language Models FMDM@NeurIPS2023 [paper][code] #minecraft #tool-use #training
[2023/03] Plan4MC: Skill Reinforcement Learning and Planning for Open-World Minecraft Tasks FMDM@NeurIPS2023 [paper][code] #minecraft #planning #training
[2023/02] Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents NeurIPS 2023 [paper][code] #minecraft #planning #prompting
[2022/07] Craft an Iron Sword: Dynamically Generating Interactive Game Characters by Prompting Large Language Models Tuned on Code Wordplay@ACL 2022 [paper] #minecraft

text-adventure

[2026/06] SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training arXiv [paper][code] #text-adventure #memory #training
[2026/06] SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale arXiv [paper] #text-adventure #memory #self-improvement
[2026/06] LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents arXiv [paper] #text-adventure
[2026/06] From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents arXiv [paper] #text-adventure #planning
[2026/06] Cross-Environment Neural Reranking for Sample-Efficient Action Selection in Text-Based Agents arXiv [paper] #text-adventure #training
[2026/06] Unified Context Evolution for LLM Agents arXiv [paper] #text-adventure
[2026/06] When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training arXiv [paper] #text-adventure #training
[2026/05] T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning arXiv [paper][code] #text-adventure #training
[2026/05] PRISM: Perception Reasoning Interleaved for Sequential Decision Making arXiv [paper] #text-adventure #vlm
[2026/05] From History to State: Constant-Context Skill Learning for LLM Agents arXiv [paper] #text-adventure #planning #training
[2026/05] StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction arXiv [paper] #text-adventure #training
[2026/05] AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning arXiv [paper] #text-adventure #training
[2026/05] Belief Memory: Agent Memory Under Partial Observability arXiv [paper] #text-adventure #memory
[2026/05] SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agents arXiv [paper] #text-adventure
[2026/05] Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents arXiv [paper] #text-adventure #training #self-improvement
[2026/05] Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning arXiv [paper] #text-adventure #tool-use #training
[2026/05] SkillMaster: Toward Autonomous Skill Mastery in LLM Agents arXiv [paper] #text-adventure #training
[2026/05] PriorZero: Bridging Language Priors and World Models for Decision Making arXiv [paper][code] #text-adventure #planning #world-model #training
[2026/05] Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents arXiv [paper] #text-adventure #memory #tool-use
[2026/05] What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents arXiv [paper] #text-adventure #training
[2026/05] APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents arXiv [paper] #text-adventure #planning #self-improvement
[2026/05] SKILLC: Learning Autonomous Skill Internalization in LLM Agents via Contrastive Credit Assignment arXiv [paper] #text-adventure #training
[2026/05] SkillsInjector: Dynamic Skill Context Construction for LLM Agents arXiv [paper] #text-adventure
[2026/05] SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs arXiv [paper] #text-adventure #memory #tool-use #training
[2026/05] Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning arXiv [paper] #text-adventure #training
[2026/05] Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents arXiv [paper] #text-adventure #memory
[2026/05] PatchBoard: Schema-Grounded State Mutation for Reliable and Auditable LLM Multi-Agent Collaboration arXiv [paper] #text-adventure #multi-agent
[2026/05] Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL arXiv [paper][code] #text-adventure #training
[2026/05] R2V Agent: Teaching SLMs When to Ask for Help arXiv [paper] #text-adventure #training
[2026/05] SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems arXiv [paper] #text-adventure #planning #memory #tool-use
[2026/04] Aligning Progress and Feasibility: A Neuro-Symbolic Dual Memory Framework for Long-Horizon LLM Agents arXiv [paper] #text-adventure #planning #memory
[2026/04] Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents arXiv [paper][code] #text-adventure #training
[2026/04] DORA Explorer: Improving the Exploration Ability of LLMs Without Training arXiv [paper] #text-adventure #planning #prompting
[2026/04] From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents arXiv [paper] #text-adventure #planning
[2026/04] Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows arXiv [paper] #text-adventure #planning #memory #multi-agent
[2026/04] ReDAct: Uncertainty-Aware Deferral for LLM Agents arXiv [paper] #text-adventure
[2026/04] GraSP: Graph-Structured Skill Compositions for LLM Agents arXiv [paper] #text-adventure #planning #memory #self-improvement
[2026/04] DPEPO: Diverse Parallel Exploration Policy Optimization for LLM-based Agents arXiv [paper][code] #text-adventure #training
[2026/03] Hindsight Credit Assignment for Long-Horizon LLM Agents arXiv [paper] #text-adventure #training
[2026/03] How Clued up are LLMs? Evaluating Multi-Step Deductive Reasoning in a Text-Based Game Environment arXiv [paper] #text-adventure #multi-agent #training
[2026/03] RPMS: Enhancing LLM-Based Embodied Planning through Rule-Augmented Memory Synergy arXiv [paper] #text-adventure #planning #memory
[2026/03] RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback arXiv [paper] #text-adventure #memory #training #self-improvement
[2026/03] Reward Prediction with Factorized World States arXiv [paper] #text-adventure #planning #prompting
[2026/02] MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents arXiv [paper] #text-adventure #self-improvement
[2026/02] Active Epistemic Control for Query-Efficient Verified Planning arXiv [paper] #text-adventure #planning
[2026/02] Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents arXiv [paper] #text-adventure #planning #training
[2026/02] TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agents arXiv [paper] #text-adventure #planning
[2026/02] CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent Pipelines arXiv [paper] #text-adventure #planning #world-model #training
[2026/02] Reinforcement World Model Learning for LLM-based Agents arXiv [paper] #text-adventure #world-model
[2026/02] SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards arXiv [paper] #text-adventure #training
[2026/02] SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning arXiv [paper][code] #text-adventure #memory #tool-use #training
[2026/01] Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memory arXiv [paper] #text-adventure
[2026/01] Beyond Entangled Planning: Task-Decoupled Planning for Long-Horizon Agents arXiv [paper] #text-adventure #planning #prompting
[2026/01] Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents arXiv [paper] #text-adventure #planning #training
[2026/01] Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates arXiv [paper][code] #text-adventure #training
[2025/12] Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2025 [paper] #text-adventure #memory
[2025/12] GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators arXiv [paper] #text-adventure
[2025/11] SkillGen: Learning Domain Skills for In-Context Sequential Decision Making arXiv [paper] #text-adventure #prompting
[2025/10] Fine-tuning with RAG for Improving LLM Learning of New Skills arXiv [paper] #text-adventure #planning #memory #training
[2025/10] GenQuest: An LLM-based Text Adventure Game for Language Learners arXiv [paper] #text-adventure #vlm #generation
[2025/10] Constrained Natural Language Action Planning for Resilient Embodied Systems arXiv [paper] #text-adventure #planning #prompting
[2025/10] The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas arXiv [paper] #text-adventure #planning
[2025/10] Graph-Enhanced Policy Optimization in LLM Agent Training arXiv [paper] #text-adventure #planning #training
[2025/10] SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph arXiv [paper] #text-adventure #training
[2025/09] World Model Implanting for Test-time Adaptation of Embodied Agents ICML 2025 poster [paper] #text-adventure #memory #world-model #prompting
[2025/09] Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent arXiv [paper] #text-adventure #planning #multi-agent #self-improvement
[2025/09] Code Driven Planning with Domain-Adaptive Critic arXiv [paper] #text-adventure #planning #self-improvement
[2025/09] Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents arXiv [paper] #text-adventure #training
[2025/09] Reflect before Act: Proactive Error Correction in Language Models arXiv [paper] #text-adventure
[2025/09] Reward Is Enough: LLMs Are In-Context Reinforcement Learners ICLR 2026 Poster [paper] #text-adventure #training #self-improvement
[2025/09] Natural Language PDDL (NL-PDDL) for Open-world Goal-oriented Commonsense Regression Planning in Embodied AI ICLR 2026 Poster [paper] #text-adventure #planning #vlm
[2025/09] Test-Time Mixture of World Models for Embodied Agents in Dynamic Environments ICLR 2026 Poster [paper] #text-adventure #prompting
[2025/09] Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations ICLR 2026 Poster [paper] #text-adventure #training
[2025/09] Dual-Scale World Memory for LLM Agents towards Hard-Exploration Problems ICLR 2026 Poster [paper] #text-adventure
[2025/09] Code Driven Planning with Domain-Adaptive Selector ICLR 2026 Poster [paper] #text-adventure #planning
[2025/09] Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization ICLR 2026 Poster [paper] #text-adventure #memory #training
[2025/09] DreamPhase: Offline Imagination and Uncertainty-Guided Planning for Large-Language-Model Agents ICLR 2026 Poster [paper] #text-adventure #planning #world-model
[2025/09] Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning ICLR 2026 Poster [paper] #text-adventure #tool-use #training
[2025/08] Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2025 [paper] #text-adventure #planning #training #vlm
[2025/07] CoEx -- Co-evolving World-model and Exploration EMNLP 2025 [paper] #text-adventure #planning #world-model
[2025/06] Enhancing Decision-Making of Large Language Models via Actor-Critic ICML 2025 poster [paper] #text-adventure #training
[2025/06] Improving LLM Agent Planning with In-Context Learning via Atomic Fact Augmentation and Lookahead Search arXiv [paper] #text-adventure #planning #world-model #training
[2025/06] StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turns arXiv [paper] #text-adventure #memory
[2025/06] OmniReflect: Discovering Transferable Constitutions for LLM agents via Neuro-Symbolic Reflections arXiv [paper] #text-adventure #planning #training #self-improvement
[2025/06] KnowMap: Efficient Knowledge-Driven Task Adaptation for LLMs arXiv [paper] #text-adventure #training
[2025/05] STORY2GAME: Generating (Almost) Everything in an Interactive Fiction Game arXiv [paper] #text-adventure #generation
[2025/05] LLM-BABYBENCH: Understanding and Evaluating Grounded Planning and Reasoning in LLMs arXiv [paper][code] #text-adventure #planning
[2025/05] Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning ICML 2025 poster [paper] #text-adventure #planning #training
[2025/05] Retrospex: Language Agent Meets Offline Reinforcement Learning Critic EMNLP 2025 [paper] #text-adventure #training
[2025/05] Agent-Environment Alignment via Automated Interface Generation arXiv [paper][code] #text-adventure #tool-use
[2025/05] Divide, Optimize, Merge: Fine-Grained LLM Agent Optimization at Scale arXiv [paper] #text-adventure
[2025/05] Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks NeurIPS 2025 poster [paper] #text-adventure
[2025/05] Learning to Play Like Humans: A Framework for LLM Adaptation in Interactive Fiction Games ACL 2025 [paper] #text-adventure
[2025/05] Training LLM-Based Agents with Synthetic Self-Reflected Trajectories and Partial Masking arXiv [paper] #text-adventure #prompting
[2025/05] SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution arXiv [paper][code] #text-adventure #training
[2025/05] ActiveVOO: Value of Observation Guided Active Knowledge Acquisition for Open-World Embodied Lifted Regression Planning NeurIPS 2025 poster [paper] #text-adventure #planning #prompting #vlm
[2025/05] SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents NeurIPS 2025 poster [paper] #text-adventure #planning #training #self-improvement
[2025/04] TALES: Text Adventure Learning Environment Suite arXiv [paper] #text-adventure
[2025/04] Monte Carlo Planning with Large Language Model for Text-Based Game Agents ICLR 2025 Poster [paper] #text-adventure #planning #training
[2025/04] Group-in-Group Policy Optimization for LLM Agent Training NeurIPS 2025 poster [paper] #text-adventure #training
[2025/03] Haunted House: A text-based game for comparing the flexibility of mental models in humans and LLMs arXiv [paper] #text-adventure
[2025/03] GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks CVPR 2025 [paper] #text-adventure #planning #training #vlm
[2025/02] TextGames: Learning to Self-Play Text-Based Puzzle Games via Language Model Reasoning. arXiv [paper] #text-adventure #self-improvement
[2025/02] Process Reward Models for LLM Agents: Practical Framework and Directions arXiv [paper][code] #text-adventure #training
[2024/12] Fine-tuning large vision-language models as decision-making agents via reinforcement learning NeurIPS 2024 [paper][code] #text-adventure #training #vlm
[2024/09] Discriminator-Guided Embodied Planning for LLM Agent ICLR 2025 Poster [paper] #text-adventure #planning
[2024/09] Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback ICLR 2025 Poster [paper] #text-adventure #planning #training #self-improvement
[2024/07] AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents ACL 2024 [paper][code] #text-adventure #tool-use
[2024/07] Arigraph: Learning knowledge graph world models with episodic memory for llm agents IJCAI 2024 [paper] #text-adventure #planning #memory
[2024/06] Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement EMNLP 2024 [paper][code] #text-adventure #self-improvement
[2024/06] STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models ACL 2024 [paper][code] #text-adventure #training
[2024/05] Agent Planning with World Knowledge Model NeurIPS 2024 [paper][code] #text-adventure #planning #memory #world-model
[2024/05] THREAD: Thinking Deeper with Recursive Spawning NAACL 2024 [paper] #text-adventure #prompting
[2024/05] Policy Improvement using Language Feedback Models NeurIPS 2024 poster [paper] #text-adventure #training
[2024/05] AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning NeurIPS 2024 poster [paper][code] #text-adventure #planning
[2024/04] Learning From Failure: Integrating Negative Examples When Fine-tuning Large Language Models as Agent arXiv [paper][code] #text-adventure #tool-use #training
[2024/04] ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy arXiv [paper] #text-adventure #planning #training #self-improvement
[2024/03] KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents NAACL 2024 [paper][code] #text-adventure #planning
[2024/03] Language Guided Exploration for RL Agents in Text Environments NAACL 2024 [paper][code] #text-adventure #training
[2024/03] Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents ACL 2024 [paper][code] #text-adventure #training #self-improvement
[2024/03] O3D: Offline Data-driven Discovery and Distillation for Sequential Decision-Making with Large Language Models COLM [paper] #text-adventure #training
[2024/03] ReAct Meets ActRe: Autonomous Annotation of Agent Trajectories for Contrastive Self-Training COLM [paper] #text-adventure #planning #training #self-improvement
[2024/03] StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows COLM [paper] #text-adventure #planning #self-improvement
[2024/02] Soft Self-Consistency Improves Language Model Agents arXiv [paper][code] #text-adventure #self-improvement
[2024/02] Empowering Large Language Model Agents through Action Learning COLM [paper][code] #text-adventure #planning #self-improvement
[2023/11] ADaPT: As-Needed Decomposition and Planning with Language Models NAACL 2023 [paper][code] #text-adventure #planning
[2023/10] FireAct: Toward Language Agent Fine-tuning arXiv [paper][code] #text-adventure #training
[2023/10] Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models ICML 2024 [paper][code] #text-adventure #planning #training
[2023/05] SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks NeurIPS 2023 [paper][code] #text-adventure #planning
[2023/04] Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions arXiv [paper] #text-adventure #world-model
[2023/03] Reflexion: Language Agents with Verbal Reinforcement Learning NeurIPS 2023 [paper][code] #text-adventure #training #self-improvement
[2022/10] ReAct: Synergizing Reasoning and Acting in Language Models ICLR 2023 [paper][code] #text-adventure #planning #training
[2022/03] ScienceWorld: Is your Agent Smarter than a 5th Grader? EMNLP 2022 [paper][code] #text-adventure
[2020/10] ALFWorld: Aligning Text and Embodied Environments for Interactive Learning ICLR 2021 [paper][code] #text-adventure #planning
[2019/09] Interactive Fiction Games: A Colossal Adventure AAAI 2020 [paper][code] #text-adventure

communication

[2026/05] Evaluating Large Language Models in a Complex Hidden Role Game arXiv [paper] #communication #planning
[2026/05] QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents arXiv [paper][code] #communication
[2026/05] MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs arXiv [paper] #communication #multi-agent
[2026/05] Playing with Words, Improving with Rewards: Training Language Models for Creative Association arXiv [paper] #communication #training
[2026/04] Trust, Lies, and Long Memories: Emergent Social Dynamics and Reputation in Multi-Round Avalon with LLM Agents arXiv [paper] #communication
[2026/03] Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information arXiv [paper] #communication #role-play
[2026/03] Deception and Communication in Autonomous Multi-Agent Systems: An Experimental Study with Among Us Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2026 [paper] #communication #multi-agent
[2026/01] Hidden in Plain Text: Measuring LLM Deception Quality Against Human Baselines Using Social Deduction Games International Conference on Agents 2027 [paper] #communication #multi-agent
[2026/01] Multicultural Spyfall: Assessing LLMs through Dynamic Multilingual Social Deduction Game arXiv [paper] #communication
[2025/12] WOLF: Werewolf-based Observations for LLM Deception and Falsehoods arXiv [paper] #communication #multi-agent
[2025/12] Measuring Fine-Grained Negotiation Tactics of Humans and LLMs in Diplomacy arXiv [paper] #communication #training
[2025/11] CSP4SDG: Constraint and Information-Theory Based Role Identification in Social Deduction Games with LLM-Enhanced Inference AAAI 2025 [paper] #communication
[2025/11] Multi-agent Undercover Gaming: Hallucination Removal via Counterfactual Test for Multimodal Reasoning arXiv [paper][code] #communication #multi-agent
[2025/10] Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategies arXiv [paper] #communication #multi-agent #self-improvement
[2025/08] Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy AAAI 2025 [paper] #communication #training
[2025/08] What to Ask Next? Probing the Imaginative Reasoning of LLMs with TurtleSoup Puzzles AAAI 2025 [paper] #communication
[2025/08] Ethical Considerations of Large Language Models in Game Playing arXiv [paper] #communication
[2025/07] CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language Games ACL 2025 [paper][code] #communication #multi-agent
[2025/07] Strategy Adaptation in Large Language Model Werewolf Agents arXiv [paper] #communication #prompting
[2025/06] WereWolf-Plus: An Update of Werewolf Game setting Based on DSGBench arXiv [paper][code] #communication #multi-agent
[2025/06] DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy ICML 2025 poster [paper] #communication #training
[2025/05] Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL NeurIPS 2025 poster [paper] #communication #planning #tool-use #training
[2025/01] DVM: Towards Controllable LLM Agents in Social Deduction Games IEEE International Conference on Acoustics, Speech, and Signal Processing 2025 [paper] #communication #training
[2024/12] Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy NeurIPS 2024 [paper][code] #communication #self-improvement
[2024/09] Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search ICLR 2025 Poster [paper] #communication #planning #multi-agent #training
[2024/06] PLAYER: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games arXiv [paper] #communication #multi-agent
[2024/05] Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf NeurIPS 2024 poster [paper] #communication #training
[2024/05] Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy NeurIPS 2024 poster [paper] #communication #planning #multi-agent #self-improvement
[2024/04] Self-playing Adversarial Language Game Enhances LLM Reasoning NeurIPS 2024 [paper][code] #communication #training #self-improvement
[2024/03] Helmsman of the Masses? Evaluate the Opinion Leadership of Large Language Models in the Werewolf Game COLM [paper] #communication #multi-agent
[2024/02] Enhance Reasoning for Large Language Models in the Game Werewolf arXiv [paper] #communication #training
[2024/02] What if LLMs Have Different World Views: Simulating Alien Civilizations with LLM-based Agents arXiv [paper] #communication
[2024/02] Can Large Language Model Agents Simulate Human Trust Behaviors? NeurIPS 2024 [paper] #communication
[2024/02] Large Language Models Fall Short: Understanding Complex Relationships in Detective Narratives ACL 2024 [paper] #communication
[2023/12] Can Large Language Models Serve as Rational Players in Game Theory? A Systematic Analysis AAAI 2024 [paper] #communication
[2023/12] Cooperation on the Fly: Exploring Language Agents for Ad Hoc Teamwork in the Avalon Game arXiv [paper] #communication #multi-agent
[2023/12] Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games ACL 2023 [paper] #communication #multi-agent #prompting
[2023/11] War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars arXiv [paper][code] #communication #multi-agent
[2023/11] clembench: Systematic Evaluation of Chat-Optimized Language Models as Conversational Agents EMNLP 2023 [paper] #communication
[2023/10] Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game ICML 2023 [paper] #communication #training
[2023/10] Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation arXiv [paper] #communication #training
[2023/10] LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay EMNLP 2023 [paper] #communication #multi-agent
[2023/10] Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models arXiv [paper][code] #communication #multi-agent
[2023/10] AvalonBench: Evaluating LLMs Playing the Game of Avalon FMDM@NeurIPS2023 [paper][code] #communication
[2023/09] Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf arXiv [paper] #communication #memory
[2023/08] GameEval: Evaluating LLMs on Conversational Games arXiv [paper][code] #communication
[2022/12] Human-Level Play in the Game of Diplomacy by Combining Language Models with Strategic Reasoning Science [paper] #communication

competition

[2026/06] Doing What They Say, Not What They Reason: Locating the Faithfulness Gap in LLM Agents arXiv [paper] #competition
[2026/06] SMAC-Talk: A Natural Language Extension of the StarCraft Multi-Agent Challenge for Large Language Models arXiv [paper] #competition #multi-agent
[2026/05] GAMBIT: A Three-Mode Benchmark for Adversarial Robustness in Multi-Agent LLM Collectives arXiv [paper] #competition #multi-agent #prompting
[2026/05] Watermarking Game-Playing Agents in Perfect-Information Extensive-Form Games arXiv [paper] #competition
[2026/05] Generalization or Memorization? Brittleness Testing for Chess-Trained Language Models arXiv [paper] #competition #training
[2026/05] PokerSkill: LLMs Can Play Expert-Level Poker without Training or Solvers arXiv [paper][code] #competition #tool-use #prompting
[2026/04] Readable Minds: Emergent Theory-of-Mind-Like Behavior in LLM Poker Agents arXiv [paper] #competition
[2026/04] MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2026 [paper] #competition #multi-agent #training
[2026/03] Grounded Chess Reasoning in Language Models via Master Distillation arXiv [paper] #competition #planning #training
[2026/03] GTO Wizard Benchmark arXiv [paper] #competition #planning #multi-agent #prompting
[2026/03] Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios arXiv [paper] #competition #planning #memory #multi-agent
[2026/02] World Models for Policy Refinement in StarCraft II arXiv [paper] #competition #world-model #prompting
[2026/02] VAM: Verbalized Action Masking for Controllable Exploration in RL Post-Training -- A Chess Case Study arXiv [paper] #competition #training
[2025/12] LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess arXiv [paper] #competition
[2025/12] Beyond Accuracy: A Geometric Stability Analysis of Large Language Models in Chess Evaluation arXiv [paper] #competition
[2025/10] Memory-Augmented State Machine Prompting: A Novel LLM Agent Framework for Real-Time Strategy Games arXiv [paper] #competition #memory
[2025/10] ChessQA: Evaluating Large Language Models for Chess Understanding arXiv [paper] #competition
[2025/10] Out-of-distribution Tests Reveal Compositionality in Chess Transformers arXiv [paper] #competition #planning
[2025/09] HLSMAC: A New StarCraft Multi-Agent Challenge for High-Level Strategic Decision-Making arXiv [paper] #competition #multi-agent #training
[2025/09] Speculative Actions: A Lossless Framework for Faster AI Agents ICLR 2026 Oral [paper] #competition #tool-use
[2025/09] SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning ICLR 2026 Poster [paper] #competition #planning #multi-agent #training
[2025/08] Tracking World States with Language Models: State-Based Evaluation Using Chess arXiv [paper] #competition
[2025/08] SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making Tasks arXiv [paper] #competition #planning #training #self-improvement
[2025/07] Learning to Imitate with Less: Efficient Individual Behavior Modeling in Chess arXiv [paper] #competition
[2025/05] Enfoque Odychess: Un método dialéctico, constructivista y adaptativo para la enseñanza del ajedrez con inteligencias artificiales generativas arXiv [paper] #competition #training
[2025/05] Can Large Language Models Master Complex Card Games? NeurIPS 2025 poster [paper][code] #competition #training
[2025/04] Explore the Reasoning Capability of LLMs in the Chess Testbed NAACL 2025 [paper] #competition
[2025/04] ZeroSumEval: Scaling LLM Evaluation with Inter-Model Competition arXiv [paper][code] #competition #planning
[2025/04] LLM-PySC2: Starcraft II learning environment for Large Language Models NeurIPS 2025 poster [paper] #competition #planning #multi-agent #vlm
[2025/04] The PokeAgent Challenge: Competitive and Long Context Learning at Scale NeurIPS Competition Track 2025 [paper] #competition
[2025/03] Society of Mind Meets Real-Time Strategy: A Hierarchical Multi-Agent Framework for Strategic Reasoning COLM 2025 [paper] #competition #multi-agent #training
[2025/02] Hierarchical Expert Prompt for Large-Language-Model: An Approach Defeat Elite AI in TextStarCraft II for the First Time arXiv [paper][code] #competition
[2025/02] Implicit Search via Discrete Diffusion: A Study on Chess ICLR 2025 Poster [paper][code] #competition #planning
[2025/01] POKERBENCH: Training Large Language Models to become Professional Poker Players AAAI 2025 [paper] #competition #planning #training
[2025/01] Complete Chess Games Enable LLM Become A Chess Master NAACL 2025 [paper] #competition #training
[2025/01] Mastering Board Games by External and Internal Planning with Language Models ICML 2025 spotlightposter [paper] #competition #planning
[2025/01] Language Models as Implicit Tree Search ICML 2025 poster [paper] #competition #planning #training
[2024/10] PokéChamp: An Expert-level Minimax Language Agent ICML 2025 [paper][code] #competition #planning
[2024/08] Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information 2024 IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) 2024 [paper] #competition #planning #multi-agent #training
[2024/05] Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models NeurIPS 2024 poster [paper] #competition
[2024/05] Reflective Multi-Agent Collaboration based on Large Language Models NeurIPS 2024 poster [paper] #competition #planning #multi-agent #training
[2024/03] Embodied LLM Agents Learn to Cooperate in Organized Teams IEEE Transactions on Computational Social Systems 2024 [paper] #competition #planning #multi-agent
[2024/02] PokéLLMon: A Human-Parity Agent for Pokémon Battles with Large Language Models TOIT 2025 [paper][code] #competition #training
[2024/02] Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization ACL 2024 [paper][code] #competition #training
[2024/01] PokerGPT: An End-to-End Lightweight Solver for Multi-Player Texas Hold'em via Large Language Model arXiv [paper] #competition #training
[2024/01] SwarmBrain: Embodied agent for real-time strategy game StarCraft II via large language models arXiv [paper] #competition #training
[2023/12] Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach NeurIPS 2024 poster [paper][code] #competition #planning
[2023/09] Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4 COLM 2024 [paper] #competition #planning #memory #prompting
[2023/08] Are ChatGPT and GPT-4 Good Poker Players?--A Pre-Flop Analysis arXiv [paper] #competition
[2023/06] ChessGPT: Bridging Policy Learning and Language Modeling NeurIPS 2023 [paper][code] #competition
[2022/10] Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task ICLR 2023 [paper] #competition

cooperation

[2026/04] Don't Make the LLM Read the Graph: Make the Graph Think arXiv [paper] #cooperation #multi-agent
[2026/03] On the Strengths and Weaknesses of Data for Open-set Embodied Assistance arXiv [paper] #cooperation #training
[2025/12] ReCollab: Retrieval-Augmented LLMs for Cooperative Ad-hoc Teammate Modeling arXiv [paper] #cooperation #memory
[2025/10] LLM-Hanabi: Evaluating Multi-Agent Gameplays with Theory-of-Mind and Rationale Inference in Imperfect Information Collaboration Game arXiv [paper] #cooperation #multi-agent
[2025/08] CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning arXiv [paper] #cooperation #planning #multi-agent #training
[2025/06] PSALM-V: Automating Symbolic Planning in Interactive Visual Environments with Large Language Models arXiv [paper] #cooperation #planning #multi-agent
[2024/05] Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration ACL 2024 [paper][code] #cooperation #planning #multi-agent #training
[2024/03] Can LLM-Augmented Autonomous Agents Cooperate?, An Evaluation of Their Cooperative Capabilities through Melting Pot IEEE Transactions on Artificial Intelligence 2024 [paper] #cooperation #multi-agent
[2024/03] ProAgent: Building Proactive Cooperative Agents with Large Language Models AAAI 2024 [paper] #cooperation
[2024/02] S-Agents: Self-organizing Agents in Open-ended Environments arXiv [paper] #cooperation
[2023/12] LLM-Powered Hierarchical Language Agent for Real-time Human-AI Coordination AAMAS 2023 [paper] #cooperation
[2023/10] Evaluating Multi-agent Coordination Abilities in Large Language Models NAACL 2023 [paper] #cooperation #planning #multi-agent #prompting
[2023/10] Theory of Mind for Multi-Agent Collaboration via Large Language Models EMNLP 2023 [paper][code] #cooperation #planning #multi-agent #training
[2023/09] MindAgent: Emergent Gaming Interaction NAACL 2023 [paper] #cooperation #planning #multi-agent #prompting
[2023/07] Building Cooperative Embodied Agents Modularly with Large Language Models ICLR 2024 [paper][code] #cooperation #planning #multi-agent #training

[2026/06] Can LLM Agents Sustain Long-Horizon Organizational Dynamics? arXiv [paper] #sim-social #planning #multi-agent
[2026/06] Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social Simulation arXiv [paper] #sim-social #multi-agent
[2026/05] GASim: A Graph-Accelerated Hybrid Framework for Social Simulation arXiv [paper][code] #sim-social #memory #multi-agent
[2026/05] ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic Profiles arXiv [paper] #sim-social #memory #multi-agent
[2026/05] ALSO: Adversarial Online Strategy Optimization for Social Agents arXiv [paper] #sim-social #multi-agent #training
[2026/05] PAVE: A Cognitive Architecture for Legitimate Violation in Generative Agent Societies arXiv [paper] #sim-social #role-play
[2026/05] APS: Bias-Controlled Adaptive Prototype Simulation for Population-Scale LLM Agents arXiv [paper] #sim-social
[2026/04] LLM-Agent-based Social Simulation for Attitude Diffusion arXiv [paper] #sim-social #memory
[2026/04] Restoring Heterogeneity in LLM-based Social Simulation: An Audience Segmentation Approach arXiv [paper] #sim-social #role-play
[2026/04] SLALOM: Simulation Lifecycle Analysis via Longitudinal Observation Metrics for Social Simulation arXiv [paper] #sim-social
[2026/04] RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents arXiv [paper] #sim-social #planning
[2026/04] Superminds Test: Actively Evaluating Collective Intelligence of Agent Society via Probing Agents arXiv [paper] #sim-social
[2026/04] Auditing Support Strategies in LLMs through Grounded Multi-Turn Social Simulation arXiv [paper] #sim-social
[2026/03] PolicySim: An LLM-Based Agent Social Simulation Sandbox for Proactive Policy Optimization WWW 2026 [paper] #sim-social #training
[2026/03] Belief-Driven Multi-Agent Collaboration via Approximate Perfect Bayesian Equilibrium for Social Simulation WWW 2026 [paper][code] #sim-social #multi-agent
[2026/02] AIvilization v0: Toward Large-Scale Artificial Social Simulation with a Unified Agent Architecture and Adaptive Agent Profiles arXiv [paper] #sim-social #planning
[2026/02] Exploring Silicon-Based Societies: An Early Study of the Moltbook Agent Community arXiv [paper] #sim-social
[2026/02] Does Socialization Emerge in AI Agent Society? A Case Study of Moltbook Proceedings of the ACM Conference on AI and Agentic Systems 2026 [paper] #sim-social
[2026/02] The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies arXiv [paper] #sim-social #multi-agent #self-improvement
[2026/01] When Agents See Humans as the Outgroup: Belief-Dependent Bias in LLM-Powered Agents arXiv [paper] #sim-social #multi-agent
[2026/01] MARO: Learning Stronger Reasoning from Social Interaction arXiv [paper] #sim-social #multi-agent
[2026/01] HumanLLM: Towards Personalized Understanding and Simulation of Human Nature arXiv [paper] #sim-social #training
[2025/12] EZYer: A simulacrum of high school with generative agent arXiv [paper] #sim-social #memory
[2025/12] Agent-Kernel: A MicroKernel Multi-Agent System Framework for Adaptive Social Simulation Powered by LLMs arXiv [paper] #sim-social #multi-agent
[2025/10] Multimodal Safety Evaluation in Generative Agent Social Simulations arXiv [paper] #sim-social #planning #vlm
[2025/10] Alita-G: Self-Evolving Generative Agent for Agent Generation arXiv [paper] #sim-social #memory #self-improvement
[2025/10] Doing Things with Words: Rethinking Theory of Mind Simulation in Large Language Models Computational Linguistics 2025 [paper] #sim-social
[2025/10] Social Simulations with Large Language Model Risk Utopian Illusion arXiv [paper] #sim-social #multi-agent
[2025/10] Emergent Coordinated Behaviors in Networked LLM Agents: Modeling the Strategic Dynamics of Information Operations WWW 2025 [paper] #sim-social
[2025/09] Implicit Behavioral Alignment of Language Agents in High-Stakes Crowd Simulations EMNLP 2025 [paper] #sim-social #role-play
[2025/09] The Emergence of Altruism in Large-Language-Model Agents Society arXiv [paper] #sim-social
[2025/07] LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra arXiv [paper][code] #sim-social #multi-agent #training #role-play
[2025/07] Too Human to Model:The Uncanny Valley of LLMs in Social Simulation -- When Generative Language Agents Misalign with Modelling Principles arXiv [paper] #sim-social
[2025/07] Validating Generative Agent-Based Models of Social Norm Enforcement: From Replication to Novel Predictions Annual Meeting of the Cognitive Science Society 2025 [paper] #sim-social #role-play
[2025/06] Empowering Economic Simulation for Massively Multiplayer Online Games through Generative Agent-Based Modeling KDD 2025 [paper] #sim-social #training
[2025/06] IndoorWorld: Integrating Physical Task Solving and Social Simulation in A Heterogeneous Multi-Agent Environment EMNLP 2025 [paper] #sim-social #multi-agent
[2025/06] AgentGroupChat-V2: Divide-and-Conquer Is What LLM-Based Multi-Agent System Need arXiv [paper][code] #sim-social #planning #multi-agent
[2025/06] Infected Smallville: How Disease Threat Shapes Sociality in LLM Agents arXiv [paper] #sim-social
[2025/05] EcoLANG: Efficient and Effective Agent Communication Language Induction for Social Simulation EMNLP 2025 [paper] #sim-social #role-play
[2025/04] SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation NAACL 2025 [paper] #sim-social #planning
[2025/04] BookWorld: From Novels to Interactive Agent Societies for Creative Story Generation arXiv [paper] #sim-social #multi-agent #generation
[2025/04] MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework NeurIPS 2025 poster [paper] #sim-social #planning #training
[2025/03] The Impact of Big Five Personality Traits on AI Agent Decision-Making in Public Spaces: A Social Simulation Study arXiv [paper] #sim-social
[2025/02] Investigating and Extending Homans' Social Exchange Theory with Large Language Model based Agents ACL 2025 [paper][code] #sim-social
[2025/01] Simulating Human-like Daily Activities with Desire-driven Autonomy ICLR 2025 [paper][code] #sim-social
[2025/01] Are Human Interactions Replicable by Generative Agents? A Case Study on Pronoun Usage in Hierarchical Interactions arXiv [paper] #sim-social
[2024/10] Project Sid: Many-agent simulations toward AI civilization arXiv [paper] #sim-social
[2024/06] Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theory arXiv [paper] #sim-social #multi-agent
[2024/05] Agent hospital: A simulacrum of hospital with evolvable medical agents arXiv [paper] #sim-social #planning
[2024/03] SOTOPIA-$\pi$: Interactive Learning of Socially Intelligent Language Agents ACL 2024 [paper][code] #sim-social #training
[2023/10] Humanoid Agents: Platform for Simulating Human-like Generative Agents EMNLP 2023 [paper] #sim-social
[2023/10] Lyfe Agents: Generative agents for low-cost real-time social interactions arXiv [paper] #sim-social #memory #multi-agent #self-improvement
[2023/10] SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents ICLR 2023 [paper][code] #sim-social #role-play
[2023/08] AgentSims: An Open-Source Sandbox for Large Language Model Evaluation arXiv [paper][code] #sim-social #planning #tool-use
[2023/07] S3: Social-network Simulation System with Large Language Model-Empowered Agents arXiv [paper] #sim-social #prompting
[2023/04] Generative Agents: Interactive Simulacra of Human Behavior UIST 2023 [paper][code] #sim-social

sim-embodied

[2026/05] Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty arXiv [paper] #sim-embodied #training
[2026/05] Probing Embodied LLMs: When Higher Observation Fidelity Hurts Problem Solving arXiv [paper] #sim-embodied
[2026/02] To Move or Not to Move: Constraint-based Planning Enables Zero-Shot Generalization for Interactive Navigation arXiv [paper] #sim-embodied #planning #prompting #vlm
[2025/12] Emergence: Overcoming Privileged Information Bias in Asymmetric Embodied Agents via Active Querying arXiv [paper] #sim-embodied
[2025/12] ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning arXiv [paper] #sim-embodied #planning #memory #training
[2025/12] HELP: Hierarchical Embodied Language Planner for Household Tasks arXiv [paper] #sim-embodied #planning
[2025/11] DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration arXiv [paper] #sim-embodied #planning #multi-agent #world-model
[2025/11] MADRA: Multi-Agent Debate for Risk-Aware Embodied Planning arXiv [paper] #sim-embodied #planning #multi-agent #prompting
[2025/09] ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures ICLR 2026 Poster [paper] #sim-embodied #planning
[2024/09] Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems ICLR 2025 Poster [paper] #sim-embodied #training
[2024/09] BadRobot: Jailbreaking Embodied LLM Agents in the Physical World ICLR 2025 Poster [paper] #sim-embodied #planning #vlm
[2024/09] GameGen-X: Interactive Open-world Game Video Generation ICLR 2025 Poster [paper][code] #sim-embodied #vlm
[2024/01] True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning arXiv [paper][code] #sim-embodied #training
[2023/10] Octopus: Embodied Vision-Language Programmer from Environmental Feedback ECCV 2023 [paper][code] #sim-embodied #planning #training #vlm
[2023/05] Language Models Meet World Models: Embodied Experiences Enhance Language Models NeurIPS 2023 [paper][code] #sim-embodied #planning #world-model
[2022/12] LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models ICCV 2023 [paper] #sim-embodied #planning #prompting
[2022/01] Language Models as Zero-ShoSSocial-network Simulation Planners: Extracting Actionable Knowledge for Embodied Agents ICML 2022 [paper][code] #sim-embodied

sim-other

[2024/01] CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents ICLR 2024 [paper][code] #sim-other

crafter

[2025/09] Goal-Guided Efficient Exploration via Large Language Model in Reinforcement Learning arXiv [paper] #crafter #planning #training
[2025/08] HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents arXiv [paper] #crafter #planning #training
[2025/06] Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback arXiv [paper] #crafter #self-improvement
[2025/02] LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning arXiv [paper] #crafter #planning #memory #multi-agent
[2024/10] Mars: Situated Inductive Reasoning in an Open-World Environment NeurIPS 2024 [paper] #crafter
[2024/07] Enhancing Agent Learning through World Dynamics Modeling EMNLP 2024 [paper] #crafter
[2024/04] AgentKit: Flow Engineering with Graphs, not Coding arXiv [paper][code] #crafter #planning
[2024/04] World Models with Hints of Large Language Models for Goal Achieving NAACL 2024 [paper] #crafter #training #vlm
[2024/03] EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents COLM [paper] #crafter #training
[2024/03] AgentKit: Structured LLM Reasoning with Dynamic Graphs COLM [paper] #crafter #planning
[2023/09] AdaRefiner: Refining Decisions of Language Models with Adaptive Feedback NAACL 2023 [paper] #crafter #training
[2023/06] OMNI: Open-endedness via Models of human Notions of Interestingness arXiv [paper][code] #crafter
[2023/05] SPRING: Studying Papers and Reasoning to play Games NeurIPS 2023 [paper] #crafter
[2023/02] Guiding Pretraining in Reinforcement Learning with Large Language Models ICML 2023 [paper] #crafter #training

action

[2026/05] Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning arXiv [paper] #action #training #vlm
[2026/05] ANO: A Principled Approach to Robust Policy Optimization arXiv [paper] #action #training
[2026/05] Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay arXiv [paper] #action #planning #training #vlm
[2026/04] Playing DOOM with 1.3M Parameters: Specialized Small Models vs Large Language Models for Real-Time Game Control arXiv [paper] #action
[2026/04] PokeGym: A Visually-Driven Long-Horizon Benchmark for Vision-Language Models arXiv [paper] #action #planning #vlm
[2026/04] GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning arXiv [paper] #action #training
[2026/03] Understanding the Challenges in Iterative Generative Optimization with LLMs arXiv [paper] #action
[2026/03] See, Symbolize, Act: Grounding VLMs with Spatial Representations for Better Gameplay arXiv [paper] #action #vlm
[2026/02] Implicit Strategic Optimization: Rethinking Long-Horizon Decision-Making in Adversarial Poker Environments arXiv [paper] #action #training
[2025/12] Robust Agents in Open-Ended Worlds arXiv [paper] #action #multi-agent #training #generation
[2025/09] Exploration with Foundation Models: Capabilities, Limitations, and Hybrid Approaches arXiv [paper] #action #training #vlm
[2025/08] A Multi-Agent Pokemon Tournament for Evaluating Strategic Reasoning of Large Language Models arXiv [paper] #action #multi-agent
[2025/08] Learning Game-Playing Agents with Generative Code Optimization arXiv [paper] #action #training #self-improvement
[2025/05] Frog Soup: Zero-Shot, In-Context, and Sample-Efficient Frogger Agents arXiv [paper][code] #action #training
[2025/05] Multiple Weaks Win Single Strong: Large Language Models Ensemble Weak Reinforcement Learning Agents into a Supreme One arXiv [paper] #action #training
[2025/05] Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs NeurIPS 2025 poster [paper] #action #training
[2025/05] LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models NeurIPS 2025 spotlight [paper][code] #action #training
[2025/05] PoE-World: Compositional World Modeling with Products of Programmatic Experts NeurIPS 2025 spotlight [paper] #action #planning #world-model
[2025/04] Better Decisions through the Right Causal World Model arXiv [paper] #action #planning #world-model #training
[2025/01] LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations ICML 2025 poster [paper] #action #planning #training
[2024/10] Unbounded: A Generative Infinite Game of Character Life Simulation ICLR 2024 [paper] #action
[2024/09] Can VLMs Play Action Role-Playing Games? Take Black Myth Wukong as a Study Case arXiv [paper][code] #action #planning #training
[2024/09] MaestroMotif: Skill Design from Artificial Intelligence Feedback ICLR 2025 Oral [paper] #action #training
[2024/09] BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games ICLR 2025 Poster [paper] #action #planning #training #vlm
[2024/08] Atari-GPT: Investigating the Capabilities of Multimodal Large Language Models as Low-Level Policies for Atari Games arXiv [paper] #action #planning #training
[2024/07] Baba Is AI: Break the Rules to Beat the Benchmark ICML 2024 [paper] #action #vlm
[2024/03] Will GPT-4 Run DOOM? IEEE Transactions on Games 2024 [paper][code] #action #planning #training
[2024/03] Evaluate LLMs in Real Time with Street Fighter III GitHub [paper][code] #action
[2023/02] Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning ICML 2023 [paper][code] #action #training

video-adventure

[2024/03] Cradle: Empowering Foundation Agents Towards General Computer Control ICML 2024 [paper][code] #video-adventure #planning
[2024/03] Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents 2024 IEEE Conference on Games (CoG) 2024 [paper][code] #video-adventure #planning #prompting
[2023/09] Motif: Intrinsic Motivation from Artificial Intelligence Feedback ICLR 2024 [paper][code] #video-adventure #training

benchmark

[2026/01] NitroGen: An Open Foundation Model for Generalist Gaming Agents arXiv [paper] #benchmark #training
[2025/10] Think Globally, Group Locally: Evaluating LLMs Using Multi-Lingual Word Grouping Games EMNLP 2025 [paper] #benchmark
[2025/06] Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games arXiv [paper][code] #benchmark #training
[2025/06] UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI ICCV 2025 [paper][code] #benchmark #multi-agent #training
[2025/05] lmgame-Bench: How Good are LLMs at Playing Games?." ICLR 2026 Poster [paper][code] #benchmark #planning #training
[2025/05] Is Your LLM Really Mastering the Concept? A Multi-Agent Benchmark arXiv [paper][code] #benchmark #multi-agent

other

[2026/04] GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents arXiv [paper] #planning #vlm
[2026/04] Nemobot Games: Crafting Strategic AI Gaming Agents for Interactive Learning with Large Language Models arXiv [paper] #tool-use #training #self-improvement
[2026/04] From World-Gen to Quest-Line: A Dependency-Driven Prompt Pipeline for Coherent RPG Generation arXiv [paper] #planning #generation
[2026/03] Sensi: Learn One Thing at a Time -- Curriculum-Based Test-Time Learning for LLM Game Agents arXiv [paper]
[2026/02] VLM-Guided Experience Replay arXiv [paper] #planning #training #vlm
[2026/01] SNAP: A Plan-Driven Framework for Controllable Interactive Narrative Generation arXiv [paper] #planning #generation
[2025/10] ROBOPSY PL[AI]: Using Role-Play to Investigate how LLMs Present Collective Memory arXiv [paper] #role-play
[2025/08] All Stories Are One Story: Emotional Arc Guided Procedural Game Level Generation arXiv [paper] #generation
[2025/08] CHBench: A Cognitive Hierarchy Benchmark for Evaluating Strategic Reasoning Capability of LLMs arXiv [paper] #memory
[2025/06] The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind arXiv [paper] #multi-agent #training
[2025/04] PAYADOR: A Minimalist Approach to Grounding Language Models on Structured Data for Interactive Storytelling and Role-playing Games arXiv [paper]
[2025/04] Enhancing Player Enjoyment with a Two-Tier DRL and LLM-Based Agent System for Fighting Games arXiv [paper] #training
[2025/03] Playing games with Large language models: Randomness and strategy arXiv [paper] #multi-agent
[2025/03] Collaborative Storytelling and LLM: A Linguistic Analysis of Automatically-Generated Role-Playing Game Sessions arXiv [paper]
[2025/03] Cultivating Game Sense for Yourself: Making VLMs Gaming Experts arXiv [paper] #vlm
[2025/02] RPGBENCH: Evaluating Large Language Models as Role-Playing Game Engines arXiv [paper]
[2025/02] Hybrid Voting-Based Task Assignment in Role-Playing Games arXiv [paper] #planning
[2024/09] Agents' Room: Narrative Generation through Multi-step Collaboration ICLR 2025 Poster [paper] #generation
[2024/07] What if Red Can Talk? Dynamic Dialogue Generation Using Large Language Models. arXiv [paper] #generation
[2023/10] Language as reality: a co-creative storytelling game experience in 1001 nights using generative AI. AAAI 2023 [paper] #generation

By Mechanism

The same papers as above, re-grouped by agent design. A paper with multiple Mechanism tags appears in each relevant section.

planning

[2026/06] Can LLM Agents Sustain Long-Horizon Organizational Dynamics? arXiv [paper] #sim-social #planning #multi-agent
[2026/06] From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents arXiv [paper] #text-adventure #planning
[2026/05] From History to State: Constant-Context Skill Learning for LLM Agents arXiv [paper] #text-adventure #planning #training
[2026/05] PriorZero: Bridging Language Priors and World Models for Decision Making arXiv [paper][code] #text-adventure #planning #world-model #training
[2026/05] Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay arXiv [paper] #action #planning #training #vlm
[2026/05] APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents arXiv [paper] #text-adventure #planning #self-improvement
[2026/05] Evaluating Large Language Models in a Complex Hidden Role Game arXiv [paper] #communication #planning
[2026/05] SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems arXiv [paper] #text-adventure #planning #memory #tool-use
[2026/04] Aligning Progress and Feasibility: A Neuro-Symbolic Dual Memory Framework for Long-Horizon LLM Agents arXiv [paper] #text-adventure #planning #memory
[2026/04] GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents arXiv [paper] #planning #vlm
[2026/04] PokeGym: A Visually-Driven Long-Horizon Benchmark for Vision-Language Models arXiv [paper] #action #planning #vlm
[2026/04] RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents arXiv [paper] #sim-social #planning
[2026/04] DORA Explorer: Improving the Exploration Ability of LLMs Without Training arXiv [paper] #text-adventure #planning #prompting
[2026/04] From Actions to Understanding: Conformal Interpretability of Temporal Concepts in LLM Agents arXiv [paper] #text-adventure #planning
[2026/04] Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows arXiv [paper] #text-adventure #planning #memory #multi-agent
[2026/04] From World-Gen to Quest-Line: A Dependency-Driven Prompt Pipeline for Coherent RPG Generation arXiv [paper] #planning #generation
[2026/04] GraSP: Graph-Structured Skill Compositions for LLM Agents arXiv [paper] #text-adventure #planning #memory #self-improvement
[2026/03] RPMS: Enhancing LLM-Based Embodied Planning through Rule-Augmented Memory Synergy arXiv [paper] #text-adventure #planning #memory
[2026/03] Grounded Chess Reasoning in Language Models via Master Distillation arXiv [paper] #competition #planning #training
[2026/03] GTO Wizard Benchmark arXiv [paper] #competition #planning #multi-agent #prompting
[2026/03] Reward Prediction with Factorized World States arXiv [paper] #text-adventure #planning #prompting
[2026/03] Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios arXiv [paper] #competition #planning #memory #multi-agent
[2026/02] VLM-Guided Experience Replay arXiv [paper] #planning #training #vlm
[2026/02] Active Epistemic Control for Query-Efficient Verified Planning arXiv [paper] #text-adventure #planning
[2026/02] AIvilization v0: Toward Large-Scale Artificial Social Simulation with a Unified Agent Architecture and Adaptive Agent Profiles arXiv [paper] #sim-social #planning
[2026/02] Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents arXiv [paper] #text-adventure #planning #training
[2026/02] TAPE: Tool-Guided Adaptive Planning and Constrained Execution in Language Model Agents arXiv [paper] #text-adventure #planning
[2026/02] To Move or Not to Move: Constraint-based Planning Enables Zero-Shot Generalization for Interactive Navigation arXiv [paper] #sim-embodied #planning #prompting #vlm
[2026/02] CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent Pipelines arXiv [paper] #text-adventure #planning #world-model #training
[2026/01] Beyond Entangled Planning: Task-Decoupled Planning for Long-Horizon Agents arXiv [paper] #text-adventure #planning #prompting
[2026/01] SNAP: A Plan-Driven Framework for Controllable Interactive Narrative Generation arXiv [paper] #planning #generation
[2026/01] Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents arXiv [paper] #text-adventure #planning #training
[2025/12] ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning arXiv [paper] #sim-embodied #planning #memory #training
[2025/12] HELP: Hierarchical Embodied Language Planner for Household Tasks arXiv [paper] #sim-embodied #planning
[2025/11] DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration arXiv [paper] #sim-embodied #planning #multi-agent #world-model
[2025/11] MADRA: Multi-Agent Debate for Risk-Aware Embodied Planning arXiv [paper] #sim-embodied #planning #multi-agent #prompting
[2025/10] Fine-tuning with RAG for Improving LLM Learning of New Skills arXiv [paper] #text-adventure #planning #memory #training
[2025/10] Constrained Natural Language Action Planning for Resilient Embodied Systems arXiv [paper] #text-adventure #planning #prompting
[2025/10] The Cognitive Bandwidth Bottleneck: Shifting Long-Horizon Agent from Planning with Actions to Planning with Schemas arXiv [paper] #text-adventure #planning
[2025/10] Multimodal Safety Evaluation in Generative Agent Social Simulations arXiv [paper] #sim-social #planning #vlm
[2025/10] Graph-Enhanced Policy Optimization in LLM Agent Training arXiv [paper] #text-adventure #planning #training
[2025/10] Out-of-distribution Tests Reveal Compositionality in Chess Transformers arXiv [paper] #competition #planning
[2025/09] Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent arXiv [paper] #text-adventure #planning #multi-agent #self-improvement
[2025/09] Code Driven Planning with Domain-Adaptive Critic arXiv [paper] #text-adventure #planning #self-improvement
[2025/09] Goal-Guided Efficient Exploration via Large Language Model in Reinforcement Learning arXiv [paper] #crafter #planning #training
[2025/09] Natural Language PDDL (NL-PDDL) for Open-world Goal-oriented Commonsense Regression Planning in Embodied AI ICLR 2026 Poster [paper] #text-adventure #planning #vlm
[2025/09] Experience-based Knowledge Correction for Robust Planning in Minecraft ICLR 2026 Poster [paper] #minecraft #planning
[2025/09] SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning ICLR 2026 Poster [paper] #competition #planning #multi-agent #training
[2025/09] Code Driven Planning with Domain-Adaptive Selector ICLR 2026 Poster [paper] #text-adventure #planning
[2025/09] ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures ICLR 2026 Poster [paper] #sim-embodied #planning
[2025/09] DreamPhase: Offline Imagination and Uncertainty-Guided Planning for Large-Language-Model Agents ICLR 2026 Poster [paper] #text-adventure #planning #world-model
[2025/08] CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks Findings of EMNLP 2025 [paper] #minecraft #planning #multi-agent
[2025/08] Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2025 [paper] #text-adventure #planning #training #vlm
[2025/08] CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning arXiv [paper] #cooperation #planning #multi-agent #training
[2025/08] SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making Tasks arXiv [paper] #competition #planning #training #self-improvement
[2025/08] HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents arXiv [paper] #crafter #planning #training
[2025/07] CoEx -- Co-evolving World-model and Exploration EMNLP 2025 [paper] #text-adventure #planning #world-model
[2025/06] Optimus-3: Towards Generalist Multimodal Minecraft Agents with Scalable Task Experts arXiv [paper][code] #minecraft #planning
[2025/06] Improving LLM Agent Planning with In-Context Learning via Atomic Fact Augmentation and Lookahead Search arXiv [paper] #text-adventure #planning #world-model #training
[2025/06] OmniReflect: Discovering Transferable Constitutions for LLM agents via Neuro-Symbolic Reflections arXiv [paper] #text-adventure #planning #training #self-improvement
[2025/06] AgentGroupChat-V2: Divide-and-Conquer Is What LLM-Based Multi-Agent System Need arXiv [paper][code] #sim-social #planning #multi-agent
[2025/06] PSALM-V: Automating Symbolic Planning in Interactive Visual Environments with Large Language Models arXiv [paper] #cooperation #planning #multi-agent
[2025/05] Don’t Just Follow MLLM Plans: Robust and Efficient Planning for Open-World Agents arXiv [paper] #minecraft #planning #vlm
[2025/05] Knowledge Retrieval in LLM Gaming: A Shift from Entity-Centric to Goal-Oriented Graphs Knowledge-Based Systems 2025 [paper] #minecraft #planning #memory
[2025/05] lmgame-Bench: How Good are LLMs at Playing Games?." ICLR 2026 Poster [paper][code] #benchmark #planning #training
[2025/05] LLM-BABYBENCH: Understanding and Evaluating Grounded Planning and Reasoning in LLMs arXiv [paper][code] #text-adventure #planning
[2025/05] Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning ICML 2025 poster [paper] #text-adventure #planning #training
[2025/05] ActiveVOO: Value of Observation Guided Active Knowledge Acquisition for Open-World Embodied Lifted Regression Planning NeurIPS 2025 poster [paper] #text-adventure #planning #prompting #vlm
[2025/05] Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL NeurIPS 2025 poster [paper] #communication #planning #tool-use #training
[2025/05] SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents NeurIPS 2025 poster [paper] #text-adventure #planning #training #self-improvement
[2025/05] PoE-World: Compositional World Modeling with Products of Programmatic Experts NeurIPS 2025 spotlight [paper] #action #planning #world-model
[2025/05] WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents NeurIPS 2025 poster [paper] #minecraft #planning #world-model #prompting
[2025/04] WALL-E 2.0: World Alignment by NeuroSymbolic Learning Improves World Model-based LLM Agents arXiv [paper][code] #minecraft #planning #world-model #prompting
[2025/04] Better Decisions through the Right Causal World Model arXiv [paper] #action #planning #world-model #training
[2025/04] ZeroSumEval: Scaling LLM Evaluation with Inter-Model Competition arXiv [paper][code] #competition #planning
[2025/04] SOTOPIA-S4: a user-friendly system for flexible, customizable, and large-scale social simulation NAACL 2025 [paper] #sim-social #planning
[2025/04] Monte Carlo Planning with Large Language Model for Text-Based Game Agents ICLR 2025 Poster [paper] #text-adventure #planning #training
[2025/04] LLM-PySC2: Starcraft II learning environment for Large Language Models NeurIPS 2025 poster [paper] #competition #planning #multi-agent #vlm
[2025/04] MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework NeurIPS 2025 poster [paper] #sim-social #planning #training
[2025/03] Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems arXiv [paper] #minecraft #planning #multi-agent #tool-use
[2025/03] GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks CVPR 2025 [paper] #text-adventure #planning #training #vlm
[2025/03] Plancraft: an evaluation dataset for planning with LLM agents COLM 2025 [paper] #minecraft #planning #memory #tool-use
[2025/02] Optimus-2: Multimodal World Model for Open-World Minecraft Agents CVPR 2025 [paper][code] #minecraft #planning #world-model #vlm
[2025/02] LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning arXiv [paper] #crafter #planning #memory #multi-agent
[2025/02] Hybrid Voting-Based Task Assignment in Role-Playing Games arXiv [paper] #planning
[2025/02] Implicit Search via Discrete Diffusion: A Study on Chess ICLR 2025 Poster [paper][code] #competition #planning
[2025/01] POKERBENCH: Training Large Language Models to become Professional Poker Players AAAI 2025 [paper] #competition #planning #training
[2025/01] Mastering Board Games by External and Internal Planning with Language Models ICML 2025 spotlightposter [paper] #competition #planning
[2025/01] LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations ICML 2025 poster [paper] #action #planning #training
[2025/01] Language Models as Implicit Tree Search ICML 2025 poster [paper] #competition #planning #training
[2024/10] WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents arXiv [paper][code] #minecraft #planning #world-model
[2024/10] ADAM: An Embodied Causal Agent in Open-World Environments ICLR 2025 [paper][code] #minecraft #planning
[2024/10] PokéChamp: An Expert-level Minimax Language Agent ICML 2025 [paper][code] #competition #planning
[2024/09] Can VLMs Play Action Role-Playing Games? Take Black Myth Wukong as a Study Case arXiv [paper][code] #action #planning #training
[2024/09] Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search ICLR 2025 Poster [paper] #communication #planning #multi-agent #training
[2024/09] Discriminator-Guided Embodied Planning for LLM Agent ICLR 2025 Poster [paper] #text-adventure #planning
[2024/09] Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback ICLR 2025 Poster [paper] #text-adventure #planning #training #self-improvement
[2024/09] BadRobot: Jailbreaking Embodied LLM Agents in the Physical World ICLR 2025 Poster [paper] #sim-embodied #planning #vlm
[2024/09] BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games ICLR 2025 Poster [paper] #action #planning #training #vlm
[2024/08] Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-horizon Tasks NeurIPS 2024 [paper][code] #minecraft #planning #memory #prompting
[2024/08] Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information 2024 IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) 2024 [paper] #competition #planning #multi-agent #training
[2024/08] Atari-GPT: Investigating the Capabilities of Multimodal Large Language Models as Low-Level Policies for Atari Games arXiv [paper] #action #planning #training
[2024/07] Arigraph: Learning knowledge graph world models with episodic memory for llm agents IJCAI 2024 [paper] #text-adventure #planning #memory
[2024/07] Odyssey: Empowering Agents with Open-World Skills. IJCAI 2024 [paper][code] #minecraft #planning #tool-use
[2024/06] VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft Findings of ACL 2024 [paper][code] #minecraft #planning #multi-agent
[2024/05] Agent Planning with World Knowledge Model NeurIPS 2024 [paper][code] #text-adventure #planning #memory #world-model
[2024/05] Agent hospital: A simulacrum of hospital with evolvable medical agents arXiv [paper] #sim-social #planning
[2024/05] Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration ACL 2024 [paper][code] #cooperation #planning #multi-agent #training
[2024/05] Reflective Multi-Agent Collaboration based on Large Language Models NeurIPS 2024 poster [paper] #competition #planning #multi-agent #training
[2024/05] AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learning NeurIPS 2024 poster [paper][code] #text-adventure #planning
[2024/05] Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy NeurIPS 2024 poster [paper] #communication #planning #multi-agent #self-improvement
[2024/04] ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy arXiv [paper] #text-adventure #planning #training #self-improvement
[2024/04] AgentKit: Flow Engineering with Graphs, not Coding arXiv [paper][code] #crafter #planning
[2024/03] KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents NAACL 2024 [paper][code] #text-adventure #planning
[2024/03] Cradle: Empowering Foundation Agents Towards General Computer Control ICML 2024 [paper][code] #video-adventure #planning
[2024/03] Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents 2024 IEEE Conference on Games (CoG) 2024 [paper][code] #video-adventure #planning #prompting
[2024/03] Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation (HAS) ICLR 2024 Workshop [paper] #minecraft #planning #multi-agent #vlm
[2024/03] Embodied LLM Agents Learn to Cooperate in Organized Teams IEEE Transactions on Computational Social Systems 2024 [paper] #competition #planning #multi-agent
[2024/03] Will GPT-4 Run DOOM? IEEE Transactions on Games 2024 [paper][code] #action #planning #training
[2024/03] ReAct Meets ActRe: Autonomous Annotation of Agent Trajectories for Contrastive Self-Training COLM [paper] #text-adventure #planning #training #self-improvement
[2024/03] StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows COLM [paper] #text-adventure #planning #self-improvement
[2024/03] AgentKit: Structured LLM Reasoning with Dynamic Graphs COLM [paper] #crafter #planning
[2024/02] Empowering Large Language Model Agents through Action Learning COLM [paper][code] #text-adventure #planning #self-improvement
[2024/02] RL-GPT: Integrating Reinforcement Learning and Code-as-policy NeurIPS 2024 oral [paper] #minecraft #planning #tool-use #training
[2023/12] MP5: A Multi-modal Open-ended Embodied System in Minecraft via Active Perception CVPR 2024 [paper][code] #minecraft #planning #vlm
[2023/12] Creative Agents: Empowering Agents with Imagination for Creative Tasks UAI 2023 [paper][code] #minecraft #planning
[2023/12] Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach NeurIPS 2024 poster [paper][code] #competition #planning
[2023/11] ADaPT: As-Needed Decomposition and Planning with Language Models NAACL 2023 [paper][code] #text-adventure #planning
[2023/11] JARVIS-1: Open-world Multi-task Agents with Memory-Augmented Multimodal Language Models TPAMI 2023 [paper][code] #minecraft #planning #memory
[2023/10] Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models ICML 2024 [paper][code] #text-adventure #planning #training
[2023/10] LLaMA Rider: Spurring Large Language Models to Explore the Open World NAACL 2023 [paper][code] #minecraft #planning #training
[2023/10] Octopus: Embodied Vision-Language Programmer from Environmental Feedback ECCV 2023 [paper][code] #sim-embodied #planning #training #vlm
[2023/10] Evaluating Multi-agent Coordination Abilities in Large Language Models NAACL 2023 [paper] #cooperation #planning #multi-agent #prompting
[2023/10] Theory of Mind for Multi-Agent Collaboration via Large Language Models EMNLP 2023 [paper][code] #cooperation #planning #multi-agent #training
[2023/09] Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4 COLM 2024 [paper] #competition #planning #memory #prompting
[2023/09] MindAgent: Emergent Gaming Interaction NAACL 2023 [paper] #cooperation #planning #multi-agent #prompting
[2023/08] AgentSims: An Open-Source Sandbox for Large Language Model Evaluation arXiv [paper][code] #sim-social #planning #tool-use
[2023/07] Building Cooperative Embodied Agents Modularly with Large Language Models ICLR 2024 [paper][code] #cooperation #planning #multi-agent #training
[2023/05] Language Models Meet World Models: Embodied Experiences Enhance Language Models NeurIPS 2023 [paper][code] #sim-embodied #planning #world-model
[2023/05] SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks NeurIPS 2023 [paper][code] #text-adventure #planning
[2023/03] Plan4MC: Skill Reinforcement Learning and Planning for Open-World Minecraft Tasks FMDM@NeurIPS2023 [paper][code] #minecraft #planning #training
[2023/02] Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents NeurIPS 2023 [paper][code] #minecraft #planning #prompting
[2022/12] LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models ICCV 2023 [paper] #sim-embodied #planning #prompting
[2022/10] ReAct: Synergizing Reasoning and Acting in Language Models ICLR 2023 [paper][code] #text-adventure #planning #training
[2020/10] ALFWorld: Aligning Text and Embodied Environments for Interactive Learning ICLR 2021 [paper][code] #text-adventure #planning

memory

[2026/06] SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training arXiv [paper][code] #text-adventure #memory #training
[2026/06] SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale arXiv [paper] #text-adventure #memory #self-improvement
[2026/05] Belief Memory: Agent Memory Under Partial Observability arXiv [paper] #text-adventure #memory
[2026/05] GASim: A Graph-Accelerated Hybrid Framework for Social Simulation arXiv [paper][code] #sim-social #memory #multi-agent
[2026/05] ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic Profiles arXiv [paper] #sim-social #memory #multi-agent
[2026/05] Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents arXiv [paper] #text-adventure #memory #tool-use
[2026/05] SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs arXiv [paper] #text-adventure #memory #tool-use #training
[2026/05] Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents arXiv [paper] #text-adventure #memory
[2026/05] SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems arXiv [paper] #text-adventure #planning #memory #tool-use
[2026/04] Aligning Progress and Feasibility: A Neuro-Symbolic Dual Memory Framework for Long-Horizon LLM Agents arXiv [paper] #text-adventure #planning #memory
[2026/04] LLM-Agent-based Social Simulation for Attitude Diffusion arXiv [paper] #sim-social #memory
[2026/04] Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows arXiv [paper] #text-adventure #planning #memory #multi-agent
[2026/04] GraSP: Graph-Structured Skill Compositions for LLM Agents arXiv [paper] #text-adventure #planning #memory #self-improvement
[2026/04] Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game arXiv [paper] #minecraft #memory #multi-agent #vlm
[2026/03] RPMS: Enhancing LLM-Based Embodied Planning through Rule-Augmented Memory Synergy arXiv [paper] #text-adventure #planning #memory
[2026/03] RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback arXiv [paper] #text-adventure #memory #training #self-improvement
[2026/03] Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios arXiv [paper] #competition #planning #memory #multi-agent
[2026/02] SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning arXiv [paper][code] #text-adventure #memory #tool-use #training
[2025/12] EZYer: A simulacrum of high school with generative agent arXiv [paper] #sim-social #memory
[2025/12] ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning arXiv [paper] #sim-embodied #planning #memory #training
[2025/12] Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2025 [paper] #text-adventure #memory
[2025/12] ReCollab: Retrieval-Augmented LLMs for Cooperative Ad-hoc Teammate Modeling arXiv [paper] #cooperation #memory
[2025/11] Knowledge Graph-enhanced Large Language Model for Incremental Game PlayTesting IEICE Transactions on Information and Systems 2025 [paper] #minecraft #memory
[2025/10] Fine-tuning with RAG for Improving LLM Learning of New Skills arXiv [paper] #text-adventure #planning #memory #training
[2025/10] Memory-Augmented State Machine Prompting: A Novel LLM Agent Framework for Real-Time Strategy Games arXiv [paper] #competition #memory
[2025/10] Alita-G: Self-Evolving Generative Agent for Agent Generation arXiv [paper] #sim-social #memory #self-improvement
[2025/09] World Model Implanting for Test-time Adaptation of Embodied Agents ICML 2025 poster [paper] #text-adventure #memory #world-model #prompting
[2025/09] Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization ICLR 2026 Poster [paper] #text-adventure #memory #training
[2025/08] Vistawise: Building Cost-effective Agent with Cross-modal Knowledge Graph for Minecraft EMNLP 2025 [paper] #minecraft #memory #tool-use
[2025/08] CHBench: A Cognitive Hierarchy Benchmark for Evaluating Strategic Reasoning Capability of LLMs arXiv [paper] #memory
[2025/06] StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turns arXiv [paper] #text-adventure #memory
[2025/05] Knowledge Retrieval in LLM Gaming: A Shift from Entity-Centric to Goal-Oriented Graphs Knowledge-Based Systems 2025 [paper] #minecraft #planning #memory
[2025/03] Plancraft: an evaluation dataset for planning with LLM agents COLM 2025 [paper] #minecraft #planning #memory #tool-use
[2025/02] LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning arXiv [paper] #crafter #planning #memory #multi-agent
[2024/11] MrSteve: Instruction-Following Agents with What-Where-When Memory ICLR 2025 [paper][code] #minecraft #memory
[2024/09] MrSteve: Instruction-Following Agents in Minecraft with What-Where-When Memory ICLR 2025 Poster [paper] #minecraft #memory
[2024/08] Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-horizon Tasks NeurIPS 2024 [paper][code] #minecraft #planning #memory #prompting
[2024/07] Arigraph: Learning knowledge graph world models with episodic memory for llm agents IJCAI 2024 [paper] #text-adventure #planning #memory
[2024/05] Agent Planning with World Knowledge Model NeurIPS 2024 [paper][code] #text-adventure #planning #memory #world-model
[2023/11] JARVIS-1: Open-world Multi-task Agents with Memory-Augmented Multimodal Language Models TPAMI 2023 [paper][code] #minecraft #planning #memory
[2023/11] See and Think: Embodied Agent in Virtual Environment ECCV 2023 [paper][code] #minecraft #memory
[2023/10] Lyfe Agents: Generative agents for low-cost real-time social interactions arXiv [paper] #sim-social #memory #multi-agent #self-improvement
[2023/09] Suspicion-Agent: Playing Imperfect Information Games with Theory of Mind Aware GPT-4 COLM 2024 [paper] #competition #planning #memory #prompting
[2023/09] Exploring Large Language Models for Communication Games: An Empirical Study on Werewolf arXiv [paper] #communication #memory

multi-agent

[2026/06] Can LLM Agents Sustain Long-Horizon Organizational Dynamics? arXiv [paper] #sim-social #planning #multi-agent
[2026/06] Think-Before-Speak: From Internal Evaluation to Public Expression in Multi-Agent Social Simulation arXiv [paper] #sim-social #multi-agent
[2026/06] SMAC-Talk: A Natural Language Extension of the StarCraft Multi-Agent Challenge for Large Language Models arXiv [paper] #competition #multi-agent
[2026/05] GASim: A Graph-Accelerated Hybrid Framework for Social Simulation arXiv [paper][code] #sim-social #memory #multi-agent
[2026/05] ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic Profiles arXiv [paper] #sim-social #memory #multi-agent
[2026/05] GAMBIT: A Three-Mode Benchmark for Adversarial Robustness in Multi-Agent LLM Collectives arXiv [paper] #competition #multi-agent #prompting
[2026/05] ALSO: Adversarial Online Strategy Optimization for Social Agents arXiv [paper] #sim-social #multi-agent #training
[2026/05] MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs arXiv [paper] #communication #multi-agent
[2026/05] PatchBoard: Schema-Grounded State Mutation for Reliable and Auditable LLM Multi-Agent Collaboration arXiv [paper] #text-adventure #multi-agent
[2026/04] MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2026 [paper] #competition #multi-agent #training
[2026/04] Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows arXiv [paper] #text-adventure #planning #memory #multi-agent
[2026/04] Don't Make the LLM Read the Graph: Make the Graph Think arXiv [paper] #cooperation #multi-agent
[2026/04] Gated Coordination for Efficient Multi-Agent Collaboration in Minecraft Game arXiv [paper] #minecraft #memory #multi-agent #vlm
[2026/03] How Clued up are LLMs? Evaluating Multi-Step Deductive Reasoning in a Text-Based Game Environment arXiv [paper] #text-adventure #multi-agent #training
[2026/03] GTO Wizard Benchmark arXiv [paper] #competition #planning #multi-agent #prompting
[2026/03] Self-Evolving Multi-Agent Framework for Efficient Decision Making in Real-Time Strategy Scenarios arXiv [paper] #competition #planning #memory #multi-agent
[2026/03] Belief-Driven Multi-Agent Collaboration via Approximate Perfect Bayesian Equilibrium for Social Simulation WWW 2026 [paper][code] #sim-social #multi-agent
[2026/03] Deception and Communication in Autonomous Multi-Agent Systems: An Experimental Study with Among Us Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2026 [paper] #communication #multi-agent
[2026/02] The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies arXiv [paper] #sim-social #multi-agent #self-improvement
[2026/01] When Agents See Humans as the Outgroup: Belief-Dependent Bias in LLM-Powered Agents arXiv [paper] #sim-social #multi-agent
[2026/01] Hidden in Plain Text: Measuring LLM Deception Quality Against Human Baselines Using Social Deduction Games International Conference on Agents 2027 [paper] #communication #multi-agent
[2026/01] MARO: Learning Stronger Reasoning from Social Interaction arXiv [paper] #sim-social #multi-agent
[2025/12] WOLF: Werewolf-based Observations for LLM Deception and Falsehoods arXiv [paper] #communication #multi-agent
[2025/12] Robust Agents in Open-Ended Worlds arXiv [paper] #action #multi-agent #training #generation
[2025/12] Agent-Kernel: A MicroKernel Multi-Agent System Framework for Adaptive Social Simulation Powered by LLMs arXiv [paper] #sim-social #multi-agent
[2025/11] DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration arXiv [paper] #sim-embodied #planning #multi-agent #world-model
[2025/11] Multi-agent Undercover Gaming: Hallucination Removal via Counterfactual Test for Multimodal Reasoning arXiv [paper][code] #communication #multi-agent
[2025/11] MADRA: Multi-Agent Debate for Risk-Aware Embodied Planning arXiv [paper] #sim-embodied #planning #multi-agent #prompting
[2025/10] LLM-Hanabi: Evaluating Multi-Agent Gameplays with Theory-of-Mind and Rationale Inference in Imperfect Information Collaboration Game arXiv [paper] #cooperation #multi-agent
[2025/10] Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategies arXiv [paper] #communication #multi-agent #self-improvement
[2025/10] Social Simulations with Large Language Model Risk Utopian Illusion arXiv [paper] #sim-social #multi-agent
[2025/09] Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent arXiv [paper] #text-adventure #planning #multi-agent #self-improvement
[2025/09] PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments 2025 IEEE Conference on Games (CoG) 2025 [paper] #minecraft #multi-agent #self-improvement
[2025/09] HLSMAC: A New StarCraft Multi-Agent Challenge for High-Level Strategic Decision-Making arXiv [paper] #competition #multi-agent #training
[2025/09] SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning ICLR 2026 Poster [paper] #competition #planning #multi-agent #training
[2025/08] CausalMACE: Causality Empowered Multi-Agents in Minecraft Cooperative Tasks Findings of EMNLP 2025 [paper] #minecraft #planning #multi-agent
[2025/08] A Multi-Agent Pokemon Tournament for Evaluating Strategic Reasoning of Large Language Models arXiv [paper] #action #multi-agent
[2025/08] CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning arXiv [paper] #cooperation #planning #multi-agent #training
[2025/07] LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra arXiv [paper][code] #sim-social #multi-agent #training #role-play
[2025/07] CoMet: Metaphor-Driven Covert Communication for Multi-Agent Language Games ACL 2025 [paper][code] #communication #multi-agent
[2025/06] UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI ICCV 2025 [paper][code] #benchmark #multi-agent #training
[2025/06] IndoorWorld: Integrating Physical Task Solving and Social Simulation in A Heterogeneous Multi-Agent Environment EMNLP 2025 [paper] #sim-social #multi-agent
[2025/06] WereWolf-Plus: An Update of Werewolf Game setting Based on DSGBench arXiv [paper][code] #communication #multi-agent
[2025/06] The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind arXiv [paper] #multi-agent #training
[2025/06] AgentGroupChat-V2: Divide-and-Conquer Is What LLM-Based Multi-Agent System Need arXiv [paper][code] #sim-social #planning #multi-agent
[2025/06] PSALM-V: Automating Symbolic Planning in Interactive Visual Environments with Large Language Models arXiv [paper] #cooperation #planning #multi-agent
[2025/05] Is Your LLM Really Mastering the Concept? A Multi-Agent Benchmark arXiv [paper][code] #benchmark #multi-agent
[2025/04] Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning arXiv [paper][code] #minecraft #multi-agent #training
[2025/04] BookWorld: From Novels to Interactive Agent Societies for Creative Story Generation arXiv [paper] #sim-social #multi-agent #generation
[2025/04] LLM-PySC2: Starcraft II learning environment for Large Language Models NeurIPS 2025 poster [paper] #competition #planning #multi-agent #vlm
[2025/03] Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems arXiv [paper] #minecraft #planning #multi-agent #tool-use
[2025/03] Playing games with Large language models: Randomness and strategy arXiv [paper] #multi-agent
[2025/03] Society of Mind Meets Real-Time Strategy: A Hierarchical Multi-Agent Framework for Strategic Reasoning COLM 2025 [paper] #competition #multi-agent #training
[2025/02] LLM-Powered Decentralized Generative Agents with Adaptive Hierarchical Knowledge Graph for Cooperative Planning arXiv [paper] #crafter #planning #memory #multi-agent
[2024/12] TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft arXiv [paper][code] #minecraft #multi-agent #training #vlm
[2024/09] Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search ICLR 2025 Poster [paper] #communication #planning #multi-agent #training
[2024/08] Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information 2024 IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) 2024 [paper] #competition #planning #multi-agent #training
[2024/06] VillagerAgent: A Graph-Based Multi-Agent Framework for Coordinating Complex Task Dependencies in Minecraft Findings of ACL 2024 [paper][code] #minecraft #planning #multi-agent
[2024/06] Artificial Leviathan: Exploring Social Evolution of LLM Agents Through the Lens of Hobbesian Social Contract Theory arXiv [paper] #sim-social #multi-agent
[2024/06] PLAYER: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games arXiv [paper] #communication #multi-agent
[2024/05] Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration ACL 2024 [paper][code] #cooperation #planning #multi-agent #training
[2024/05] Reflective Multi-Agent Collaboration based on Large Language Models NeurIPS 2024 poster [paper] #competition #planning #multi-agent #training
[2024/05] Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy NeurIPS 2024 poster [paper] #communication #planning #multi-agent #self-improvement
[2024/03] MineLand: Simulating Large-Scale Multi-Agent Interactions with Limited Multimodal Senses and Physical Needs arXiv [paper][code] #minecraft #multi-agent #vlm
[2024/03] Hierarchical Auto-Organizing System for Open-Ended Multi-Agent Navigation (HAS) ICLR 2024 Workshop [paper] #minecraft #planning #multi-agent #vlm
[2024/03] Embodied LLM Agents Learn to Cooperate in Organized Teams IEEE Transactions on Computational Social Systems 2024 [paper] #competition #planning #multi-agent
[2024/03] Can LLM-Augmented Autonomous Agents Cooperate?, An Evaluation of Their Cooperative Capabilities through Melting Pot IEEE Transactions on Artificial Intelligence 2024 [paper] #cooperation #multi-agent
[2024/03] Helmsman of the Masses? Evaluate the Opinion Leadership of Large Language Models in the Werewolf Game COLM [paper] #communication #multi-agent
[2023/12] Cooperation on the Fly: Exploring Language Agents for Ad Hoc Teamwork in the Avalon Game arXiv [paper] #communication #multi-agent
[2023/12] Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games ACL 2023 [paper] #communication #multi-agent #prompting
[2023/11] War and Peace (WarAgent): Large Language Model-based Multi-Agent Simulation of World Wars arXiv [paper][code] #communication #multi-agent
[2023/10] Lyfe Agents: Generative agents for low-cost real-time social interactions arXiv [paper] #sim-social #memory #multi-agent #self-improvement
[2023/10] Evaluating Multi-agent Coordination Abilities in Large Language Models NAACL 2023 [paper] #cooperation #planning #multi-agent #prompting
[2023/10] Theory of Mind for Multi-Agent Collaboration via Large Language Models EMNLP 2023 [paper][code] #cooperation #planning #multi-agent #training
[2023/10] LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay EMNLP 2023 [paper] #communication #multi-agent
[2023/10] Leveraging Word Guessing Games to Assess the Intelligence of Large Language Models arXiv [paper][code] #communication #multi-agent
[2023/09] MindAgent: Emergent Gaming Interaction NAACL 2023 [paper] #cooperation #planning #multi-agent #prompting
[2023/07] Building Cooperative Embodied Agents Modularly with Large Language Models ICLR 2024 [paper][code] #cooperation #planning #multi-agent #training

world-model

[2026/05] PriorZero: Bridging Language Priors and World Models for Decision Making arXiv [paper][code] #text-adventure #planning #world-model #training
[2026/02] World Models for Policy Refinement in StarCraft II arXiv [paper] #competition #world-model #prompting
[2026/02] CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent Pipelines arXiv [paper] #text-adventure #planning #world-model #training
[2026/02] Reinforcement World Model Learning for LLM-based Agents arXiv [paper] #text-adventure #world-model
[2025/11] DR. WELL: Dynamic Reasoning and Learning with Symbolic World Model for Embodied LLM-Based Multi-Agent Collaboration arXiv [paper] #sim-embodied #planning #multi-agent #world-model
[2025/09] World Model Implanting for Test-time Adaptation of Embodied Agents ICML 2025 poster [paper] #text-adventure #memory #world-model #prompting
[2025/09] DreamPhase: Offline Imagination and Uncertainty-Guided Planning for Large-Language-Model Agents ICLR 2026 Poster [paper] #text-adventure #planning #world-model
[2025/07] CoEx -- Co-evolving World-model and Exploration EMNLP 2025 [paper] #text-adventure #planning #world-model
[2025/06] Improving LLM Agent Planning with In-Context Learning via Atomic Fact Augmentation and Lookahead Search arXiv [paper] #text-adventure #planning #world-model #training
[2025/05] PoE-World: Compositional World Modeling with Products of Programmatic Experts NeurIPS 2025 spotlight [paper] #action #planning #world-model
[2025/05] WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents NeurIPS 2025 poster [paper] #minecraft #planning #world-model #prompting
[2025/04] WALL-E 2.0: World Alignment by NeuroSymbolic Learning Improves World Model-based LLM Agents arXiv [paper][code] #minecraft #planning #world-model #prompting
[2025/04] Better Decisions through the Right Causal World Model arXiv [paper] #action #planning #world-model #training
[2025/02] Optimus-2: Multimodal World Model for Open-World Minecraft Agents CVPR 2025 [paper][code] #minecraft #planning #world-model #vlm
[2024/10] WALL-E: World Alignment by Rule Learning Improves World Model-based LLM Agents arXiv [paper][code] #minecraft #planning #world-model
[2024/05] Agent Planning with World Knowledge Model NeurIPS 2024 [paper][code] #text-adventure #planning #memory #world-model
[2023/05] Language Models Meet World Models: Embodied Experiences Enhance Language Models NeurIPS 2023 [paper][code] #sim-embodied #planning #world-model
[2023/04] Can Large Language Models Play Text Games Well? Current State-of-the-Art and Open Questions arXiv [paper] #text-adventure #world-model

tool-use

[2026/05] Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning arXiv [paper] #text-adventure #tool-use #training
[2026/05] Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents arXiv [paper] #text-adventure #memory #tool-use
[2026/05] PokerSkill: LLMs Can Play Expert-Level Poker without Training or Solvers arXiv [paper][code] #competition #tool-use #prompting
[2026/05] SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs arXiv [paper] #text-adventure #memory #tool-use #training
[2026/05] SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems arXiv [paper] #text-adventure #planning #memory #tool-use
[2026/04] Nemobot Games: Crafting Strategic AI Gaming Agents for Interactive Learning with Large Language Models arXiv [paper] #tool-use #training #self-improvement
[2026/02] SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning arXiv [paper][code] #text-adventure #memory #tool-use #training
[2025/09] Speculative Actions: A Lossless Framework for Faster AI Agents ICLR 2026 Oral [paper] #competition #tool-use
[2025/09] Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning ICLR 2026 Poster [paper] #text-adventure #tool-use #training
[2025/08] Vistawise: Building Cost-effective Agent with Cross-modal Knowledge Graph for Minecraft EMNLP 2025 [paper] #minecraft #memory #tool-use
[2025/05] Agent-Environment Alignment via Automated Interface Generation arXiv [paper][code] #text-adventure #tool-use
[2025/05] Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL NeurIPS 2025 poster [paper] #communication #planning #tool-use #training
[2025/03] Parallelized Planning-Acting for Efficient LLM-based Multi-Agent Systems arXiv [paper] #minecraft #planning #multi-agent #tool-use
[2025/03] Plancraft: an evaluation dataset for planning with LLM agents COLM 2025 [paper] #minecraft #planning #memory #tool-use
[2024/07] AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agents ACL 2024 [paper][code] #text-adventure #tool-use
[2024/07] Odyssey: Empowering Agents with Open-World Skills. IJCAI 2024 [paper][code] #minecraft #planning #tool-use
[2024/04] Learning From Failure: Integrating Negative Examples When Fine-tuning Large Language Models as Agent arXiv [paper][code] #text-adventure #tool-use #training
[2024/02] RL-GPT: Integrating Reinforcement Learning and Code-as-policy NeurIPS 2024 oral [paper] #minecraft #planning #tool-use #training
[2023/08] AgentSims: An Open-Source Sandbox for Large Language Model Evaluation arXiv [paper][code] #sim-social #planning #tool-use
[2023/05] VOYAGER: An Open-Ended Embodied Agent with Large Language Models FMDM@NeurIPS2023 [paper][code] #minecraft #tool-use #training

training

[2026/06] SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training arXiv [paper][code] #text-adventure #memory #training
[2026/06] Cross-Environment Neural Reranking for Sample-Efficient Action Selection in Text-Based Agents arXiv [paper] #text-adventure #training
[2026/06] When Denser Credit Is Not Enough: Evidence-Calibrated Policy Optimization for Long-Horizon LLM Agent Training arXiv [paper] #text-adventure #training
[2026/05] Odysseus: Scaling VLMs to 100+ Turn Decision-Making in Games via Reinforcement Learning arXiv [paper] #action #training #vlm
[2026/05] T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning arXiv [paper][code] #text-adventure #training
[2026/05] ANO: A Principled Approach to Robust Policy Optimization arXiv [paper] #action #training
[2026/05] From History to State: Constant-Context Skill Learning for LLM Agents arXiv [paper] #text-adventure #planning #training
[2026/05] StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction arXiv [paper] #text-adventure #training
[2026/05] AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning arXiv [paper] #text-adventure #training
[2026/05] Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents arXiv [paper] #text-adventure #training #self-improvement
[2026/05] Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning arXiv [paper] #text-adventure #tool-use #training
[2026/05] SkillMaster: Toward Autonomous Skill Mastery in LLM Agents arXiv [paper] #text-adventure #training
[2026/05] Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty arXiv [paper] #sim-embodied #training
[2026/05] PriorZero: Bridging Language Priors and World Models for Decision Making arXiv [paper][code] #text-adventure #planning #world-model #training
[2026/05] Generalization or Memorization? Brittleness Testing for Chess-Trained Language Models arXiv [paper] #competition #training
[2026/05] ALSO: Adversarial Online Strategy Optimization for Social Agents arXiv [paper] #sim-social #multi-agent #training
[2026/05] Brain alignment of reasoning and action representations from vision-language and action models during naturalistic gameplay arXiv [paper] #action #planning #training #vlm
[2026/05] What and When to Distill: Selective Hindsight Distillation for Multi-Turn Agents arXiv [paper] #text-adventure #training
[2026/05] GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents arXiv [paper] #minecraft #training #vlm
[2026/05] SKILLC: Learning Autonomous Skill Internalization in LLM Agents via Contrastive Credit Assignment arXiv [paper] #text-adventure #training
[2026/05] SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs arXiv [paper] #text-adventure #memory #tool-use #training
[2026/05] Dynamic Skill Lifecycle Management for Agentic Reinforcement Learning arXiv [paper] #text-adventure #training
[2026/05] Playing with Words, Improving with Rewards: Training Language Models for Creative Association arXiv [paper] #communication #training
[2026/05] Selective Rollout: Mid-Trajectory Termination for Multi-Sample Agent RL arXiv [paper][code] #text-adventure #training
[2026/05] R2V Agent: Teaching SLMs When to Ask for Help arXiv [paper] #text-adventure #training
[2026/04] MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2026 [paper] #competition #multi-agent #training
[2026/04] Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents arXiv [paper][code] #text-adventure #training
[2026/04] GRAIL: Autonomous Concept Grounding for Neuro-Symbolic Reinforcement Learning arXiv [paper] #action #training
[2026/04] Nemobot Games: Crafting Strategic AI Gaming Agents for Interactive Learning with Large Language Models arXiv [paper] #tool-use #training #self-improvement
[2026/04] DPEPO: Diverse Parallel Exploration Policy Optimization for LLM-based Agents arXiv [paper][code] #text-adventure #training
[2026/03] On the Strengths and Weaknesses of Data for Open-set Embodied Assistance arXiv [paper] #cooperation #training
[2026/03] Hindsight Credit Assignment for Long-Horizon LLM Agents arXiv [paper] #text-adventure #training
[2026/03] How Clued up are LLMs? Evaluating Multi-Step Deductive Reasoning in a Text-Based Game Environment arXiv [paper] #text-adventure #multi-agent #training
[2026/03] PolicySim: An LLM-Based Agent Social Simulation Sandbox for Proactive Policy Optimization WWW 2026 [paper] #sim-social #training
[2026/03] Grounded Chess Reasoning in Language Models via Master Distillation arXiv [paper] #competition #planning #training
[2026/03] RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback arXiv [paper] #text-adventure #memory #training #self-improvement
[2026/02] VLM-Guided Experience Replay arXiv [paper] #planning #training #vlm
[2026/02] Implicit Strategic Optimization: Rethinking Long-Horizon Decision-Making in Adversarial Poker Environments arXiv [paper] #action #training
[2026/02] Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents arXiv [paper] #text-adventure #planning #training
[2026/02] VAM: Verbalized Action Masking for Controllable Exploration in RL Post-Training -- A Chess Case Study arXiv [paper] #competition #training
[2026/02] CWM: Contrastive World Models for Action Feasibility Learning in Embodied Agent Pipelines arXiv [paper] #text-adventure #planning #world-model #training
[2026/02] SELAUR: Self Evolving LLM Agent via Uncertainty-aware Rewards arXiv [paper] #text-adventure #training
[2026/02] SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning arXiv [paper][code] #text-adventure #memory #tool-use #training
[2026/01] NitroGen: An Open Foundation Model for Generalist Gaming Agents arXiv [paper] #benchmark #training
[2026/01] Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents arXiv [paper] #text-adventure #planning #training
[2026/01] Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates arXiv [paper][code] #text-adventure #training
[2026/01] HumanLLM: Towards Personalized Understanding and Simulation of Human Nature arXiv [paper] #sim-social #training
[2025/12] Synergizing Code Coverage and Gameplay Intent: Coverage-Aware Game Playtesting with LLM-Guided Reinforcement Learning arXiv [paper] #minecraft #training
[2025/12] ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning arXiv [paper] #sim-embodied #planning #memory #training
[2025/12] Measuring Fine-Grained Negotiation Tactics of Humans and LLMs in Diplomacy arXiv [paper] #communication #training
[2025/12] Robust Agents in Open-Ended Worlds arXiv [paper] #action #multi-agent #training #generation
[2025/10] Fine-tuning with RAG for Improving LLM Learning of New Skills arXiv [paper] #text-adventure #planning #memory #training
[2025/10] Graph-Enhanced Policy Optimization in LLM Agent Training arXiv [paper] #text-adventure #planning #training
[2025/10] SALT: Step-level Advantage Assignment for Long-horizon Agents via Trajectory Graph arXiv [paper] #text-adventure #training
[2025/09] HLSMAC: A New StarCraft Multi-Agent Challenge for High-Level Strategic Decision-Making arXiv [paper] #competition #multi-agent #training
[2025/09] Exploration with Foundation Models: Capabilities, Limitations, and Hybrid Approaches arXiv [paper] #action #training #vlm
[2025/09] Harnessing Uncertainty: Entropy-Modulated Policy Gradients for Long-Horizon LLM Agents arXiv [paper] #text-adventure #training
[2025/09] Goal-Guided Efficient Exploration via Large Language Model in Reinforcement Learning arXiv [paper] #crafter #planning #training
[2025/09] Reward Is Enough: LLMs Are In-Context Reinforcement Learners ICLR 2026 Poster [paper] #text-adventure #training #self-improvement
[2025/09] Spinning Straw into Gold: Relabeling LLM Agent Trajectories in Hindsight for Successful Demonstrations ICLR 2026 Poster [paper] #text-adventure #training
[2025/09] SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning ICLR 2026 Poster [paper] #competition #planning #multi-agent #training
[2025/09] Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization ICLR 2026 Poster [paper] #text-adventure #memory #training
[2025/09] Learn the Ropes, Then Trust the Wins: Self-imitation with Progressive Exploration for Agentic Reinforcement Learning ICLR 2026 Poster [paper] #text-adventure #tool-use #training
[2025/08] Enhancing Vision-Language Model Training with Reinforcement Learning in Synthetic Worlds for Real-World Success Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems 2025 [paper] #text-adventure #planning #training #vlm
[2025/08] Democratizing Diplomacy: A Harness for Evaluating Any Large Language Model on Full-Press Diplomacy AAAI 2025 [paper] #communication #training
[2025/08] CausalPlan: Empowering Efficient LLM Multi-Agent Collaboration Through Causality-Driven Planning arXiv [paper] #cooperation #planning #multi-agent #training
[2025/08] Learning Game-Playing Agents with Generative Code Optimization arXiv [paper] #action #training #self-improvement
[2025/08] SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making Tasks arXiv [paper] #competition #planning #training #self-improvement
[2025/08] HERAKLES: Hierarchical Skill Compilation for Open-ended LLM Agents arXiv [paper] #crafter #planning #training
[2025/07] LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra arXiv [paper][code] #sim-social #multi-agent #training #role-play
[2025/06] Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games arXiv [paper][code] #benchmark #training
[2025/06] UnrealZoo: Enriching Photo-realistic Virtual Worlds for Embodied AI ICCV 2025 [paper][code] #benchmark #multi-agent #training
[2025/06] Empowering Economic Simulation for Massively Multiplayer Online Games through Generative Agent-Based Modeling KDD 2025 [paper] #sim-social #training
[2025/06] Enhancing Decision-Making of Large Language Models via Actor-Critic ICML 2025 poster [paper] #text-adventure #training
[2025/06] Improving LLM Agent Planning with In-Context Learning via Atomic Fact Augmentation and Lookahead Search arXiv [paper] #text-adventure #planning #world-model #training
[2025/06] DipLLM: Fine-Tuning LLM for Strategic Decision-making in Diplomacy ICML 2025 poster [paper] #communication #training
[2025/06] OmniReflect: Discovering Transferable Constitutions for LLM agents via Neuro-Symbolic Reflections arXiv [paper] #text-adventure #planning #training #self-improvement
[2025/06] The Decrypto Benchmark for Multi-Agent Reasoning and Theory of Mind arXiv [paper] #multi-agent #training
[2025/06] GuessBench: Sensemaking Multimodal Creativity in the Wild arXiv [paper] #minecraft #training #vlm
[2025/06] KnowMap: Efficient Knowledge-Driven Task Adaptation for LLMs arXiv [paper] #text-adventure #training
[2025/05] lmgame-Bench: How Good are LLMs at Playing Games?." ICLR 2026 Poster [paper][code] #benchmark #planning #training
[2025/05] Frog Soup: Zero-Shot, In-Context, and Sample-Efficient Frogger Agents arXiv [paper][code] #action #training
[2025/05] Enfoque Odychess: Un método dialéctico, constructivista y adaptativo para la enseñanza del ajedrez con inteligencias artificiales generativas arXiv [paper] #competition #training
[2025/05] Multiple Weaks Win Single Strong: Large Language Models Ensemble Weak Reinforcement Learning Agents into a Supreme One arXiv [paper] #action #training
[2025/05] Divide and Conquer: Grounding LLMs as Efficient Decision-Making Agents via Offline Hierarchical Reinforcement Learning ICML 2025 poster [paper] #text-adventure #planning #training
[2025/05] Retrospex: Language Agent Meets Offline Reinforcement Learning Critic EMNLP 2025 [paper] #text-adventure #training
[2025/05] SPA-RL: Reinforcing LLM Agents via Stepwise Progress Attribution arXiv [paper][code] #text-adventure #training
[2025/05] Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs NeurIPS 2025 poster [paper] #action #training
[2025/05] Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL NeurIPS 2025 poster [paper] #communication #planning #tool-use #training
[2025/05] Can Large Language Models Master Complex Card Games? NeurIPS 2025 poster [paper][code] #competition #training
[2025/05] MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning NeurIPS 2025 poster [paper] #minecraft #training
[2025/05] SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents NeurIPS 2025 poster [paper] #text-adventure #planning #training #self-improvement
[2025/05] LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models NeurIPS 2025 spotlight [paper][code] #action #training
[2025/04] Collaborating Action by Action: A Multi-agent LLM Framework for Embodied Reasoning arXiv [paper][code] #minecraft #multi-agent #training
[2025/04] Better Decisions through the Right Causal World Model arXiv [paper] #action #planning #world-model #training
[2025/04] Enhancing Player Enjoyment with a Two-Tier DRL and LLM-Based Agent System for Fighting Games arXiv [paper] #training
[2025/04] Monte Carlo Planning with Large Language Model for Text-Based Game Agents ICLR 2025 Poster [paper] #text-adventure #planning #training
[2025/04] MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework NeurIPS 2025 poster [paper] #sim-social #planning #training
[2025/04] Group-in-Group Policy Optimization for LLM Agent Training NeurIPS 2025 poster [paper] #text-adventure #training
[2025/03] GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks CVPR 2025 [paper] #text-adventure #planning #training #vlm
[2025/03] Society of Mind Meets Real-Time Strategy: A Hierarchical Multi-Agent Framework for Strategic Reasoning COLM 2025 [paper] #competition #multi-agent #training
[2025/02] Process Reward Models for LLM Agents: Practical Framework and Directions arXiv [paper][code] #text-adventure #training
[2025/01] POKERBENCH: Training Large Language Models to become Professional Poker Players AAAI 2025 [paper] #competition #planning #training
[2025/01] DVM: Towards Controllable LLM Agents in Social Deduction Games IEEE International Conference on Acoustics, Speech, and Signal Processing 2025 [paper] #communication #training
[2025/01] Complete Chess Games Enable LLM Become A Chess Master NAACL 2025 [paper] #competition #training
[2025/01] LMAct: A Benchmark for In-Context Imitation Learning with Long Multimodal Demonstrations ICML 2025 poster [paper] #action #planning #training
[2025/01] Language Models as Implicit Tree Search ICML 2025 poster [paper] #competition #planning #training
[2025/01] LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence ICML 2025 poster [paper] #minecraft #training
[2024/12] TeamCraft: A Benchmark for Multi-Modal Multi-Agent Systems in Minecraft arXiv [paper][code] #minecraft #multi-agent #training #vlm
[2024/12] Fine-tuning large vision-language models as decision-making agents via reinforcement learning NeurIPS 2024 [paper][code] #text-adventure #training #vlm
[2024/09] Can VLMs Play Action Role-Playing Games? Take Black Myth Wukong as a Study Case arXiv [paper][code] #action #planning #training
[2024/09] Strategist: Self-improvement of LLM Decision Making via Bi-Level Tree Search ICLR 2025 Poster [paper] #communication #planning #multi-agent #training
[2024/09] MaestroMotif: Skill Design from Artificial Intelligence Feedback ICLR 2025 Oral [paper] #action #training
[2024/09] Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-Based Decision-Making Systems ICLR 2025 Poster [paper] #sim-embodied #training
[2024/09] Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback ICLR 2025 Poster [paper] #text-adventure #planning #training #self-improvement
[2024/09] BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games ICLR 2025 Poster [paper] #action #planning #training #vlm
[2024/08] Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information 2024 IEEE/WIC International Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT) 2024 [paper] #competition #planning #multi-agent #training
[2024/08] Atari-GPT: Investigating the Capabilities of Multimodal Large Language Models as Low-Level Policies for Atari Games arXiv [paper] #action #planning #training
[2024/07] OmniJARVIS: Omni-Modal Open-World Agents in Minecraft NeurIPS 2024 [paper][code] #minecraft #training #vlm
[2024/06] STARLING: Self-supervised Training of Text-based Reinforcement Learning Agent with Large Language Models ACL 2024 [paper][code] #text-adventure #training
[2024/05] Towards Efficient LLM Grounding for Embodied Multi-Agent Collaboration ACL 2024 [paper][code] #cooperation #planning #multi-agent #training
[2024/05] Policy Improvement using Language Feedback Models NeurIPS 2024 poster [paper] #text-adventure #training
[2024/05] Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf NeurIPS 2024 poster [paper] #communication #training
[2024/05] Reflective Multi-Agent Collaboration based on Large Language Models NeurIPS 2024 poster [paper] #competition #planning #multi-agent #training
[2024/04] Learning From Failure: Integrating Negative Examples When Fine-tuning Large Language Models as Agent arXiv [paper][code] #text-adventure #tool-use #training
[2024/04] ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy arXiv [paper] #text-adventure #planning #training #self-improvement
[2024/04] World Models with Hints of Large Language Models for Goal Achieving NAACL 2024 [paper] #crafter #training #vlm
[2024/04] Self-playing Adversarial Language Game Enhances LLM Reasoning NeurIPS 2024 [paper][code] #communication #training #self-improvement
[2024/03] Language Guided Exploration for RL Agents in Text Environments NAACL 2024 [paper][code] #text-adventure #training
[2024/03] Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents ACL 2024 [paper][code] #text-adventure #training #self-improvement
[2024/03] EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents COLM [paper] #crafter #training
[2024/03] SOTOPIA-$\pi$: Interactive Learning of Socially Intelligent Language Agents ACL 2024 [paper][code] #sim-social #training
[2024/03] Will GPT-4 Run DOOM? IEEE Transactions on Games 2024 [paper][code] #action #planning #training
[2024/03] O3D: Offline Data-driven Discovery and Distillation for Sequential Decision-Making with Large Language Models COLM [paper] #text-adventure #training
[2024/03] ReAct Meets ActRe: Autonomous Annotation of Agent Trajectories for Contrastive Self-Training COLM [paper] #text-adventure #planning #training #self-improvement
[2024/02] RL-GPT: Integrating Reinforcement Learning and Code-as-policy NeurIPS 2024 oral [paper] #minecraft #planning #tool-use #training
[2024/02] PokéLLMon: A Human-Parity Agent for Pokémon Battles with Large Language Models TOIT 2025 [paper][code] #competition #training
[2024/02] Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization ACL 2024 [paper][code] #competition #training
[2024/02] Enhance Reasoning for Large Language Models in the Game Werewolf arXiv [paper] #communication #training
[2024/01] True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning arXiv [paper][code] #sim-embodied #training
[2024/01] PokerGPT: An End-to-End Lightweight Solver for Multi-Player Texas Hold'em via Large Language Model arXiv [paper] #competition #training
[2024/01] SwarmBrain: Embodied agent for real-time strategy game StarCraft II via large language models arXiv [paper] #competition #training
[2023/12] Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft CVPR 2023 [paper] #minecraft #training
[2023/10] FireAct: Toward Language Agent Fine-tuning arXiv [paper][code] #text-adventure #training
[2023/10] Language Agent Tree Search Unifies Reasoning Acting and Planning in Language Models ICML 2024 [paper][code] #text-adventure #planning #training
[2023/10] LLaMA Rider: Spurring Large Language Models to Explore the Open World NAACL 2023 [paper][code] #minecraft #planning #training
[2023/10] Octopus: Embodied Vision-Language Programmer from Environmental Feedback ECCV 2023 [paper][code] #sim-embodied #planning #training #vlm
[2023/10] Theory of Mind for Multi-Agent Collaboration via Large Language Models EMNLP 2023 [paper][code] #cooperation #planning #multi-agent #training
[2023/10] Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game ICML 2023 [paper] #communication #training
[2023/10] Avalon's Game of Thoughts: Battle Against Deception through Recursive Contemplation arXiv [paper] #communication #training
[2023/09] Motif: Intrinsic Motivation from Artificial Intelligence Feedback ICLR 2024 [paper][code] #video-adventure #training
[2023/09] AdaRefiner: Refining Decisions of Language Models with Adaptive Feedback NAACL 2023 [paper] #crafter #training
[2023/07] Building Cooperative Embodied Agents Modularly with Large Language Models ICLR 2024 [paper][code] #cooperation #planning #multi-agent #training
[2023/05] Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory arXiv [paper] #minecraft #training
[2023/05] VOYAGER: An Open-Ended Embodied Agent with Large Language Models FMDM@NeurIPS2023 [paper][code] #minecraft #tool-use #training
[2023/03] Plan4MC: Skill Reinforcement Learning and Planning for Open-World Minecraft Tasks FMDM@NeurIPS2023 [paper][code] #minecraft #planning #training
[2023/03] Reflexion: Language Agents with Verbal Reinforcement Learning NeurIPS 2023 [paper][code] #text-adventure #training #self-improvement
[2023/02] Guiding Pretraining in Reinforcement Learning with Large Language Models ICML 2023 [paper] #crafter #training
[2023/02] Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning ICML 2023 [paper][code] #action #training
[2022/10] ReAct: Synergizing Reasoning and Acting in Language Models ICLR 2023 [paper][code] #text-adventure #planning #training

self-improvement

[2026/06] SkillDAG: Self-Evolving Typed Skill Graphs for LLM Skill Selection at Scale arXiv [paper] #text-adventure #memory #self-improvement
[2026/05] Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agents arXiv [paper] #text-adventure #training #self-improvement
[2026/05] APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents arXiv [paper] #text-adventure #planning #self-improvement
[2026/05] Ratchet: A Minimal Hygiene Recipe for Self-Evolving LLM Agents arXiv [paper] #minecraft #self-improvement
[2026/04] Nemobot Games: Crafting Strategic AI Gaming Agents for Interactive Learning with Large Language Models arXiv [paper] #tool-use #training #self-improvement
[2026/04] GraSP: Graph-Structured Skill Compositions for LLM Agents arXiv [paper] #text-adventure #planning #memory #self-improvement
[2026/03] RetroAgent: From Solving to Evolving via Retrospective Dual Intrinsic Feedback arXiv [paper] #text-adventure #memory #training #self-improvement
[2026/02] MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents arXiv [paper] #text-adventure #self-improvement
[2026/02] The Devil Behind Moltbook: Anthropic Safety is Always Vanishing in Self-Evolving AI Societies arXiv [paper] #sim-social #multi-agent #self-improvement
[2025/10] Alita-G: Self-Evolving Generative Agent for Agent Generation arXiv [paper] #sim-social #memory #self-improvement
[2025/10] Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategies arXiv [paper] #communication #multi-agent #self-improvement
[2025/09] Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent arXiv [paper] #text-adventure #planning #multi-agent #self-improvement
[2025/09] PillagerBench: Benchmarking LLM-Based Agents in Competitive Minecraft Team Environments 2025 IEEE Conference on Games (CoG) 2025 [paper] #minecraft #multi-agent #self-improvement
[2025/09] Code Driven Planning with Domain-Adaptive Critic arXiv [paper] #text-adventure #planning #self-improvement
[2025/09] Reward Is Enough: LLMs Are In-Context Reinforcement Learners ICLR 2026 Poster [paper] #text-adventure #training #self-improvement
[2025/08] Learning Game-Playing Agents with Generative Code Optimization arXiv [paper] #action #training #self-improvement
[2025/08] SC2Arena and StarEvolve: Benchmark and Self-Improvement Framework for LLMs in Complex Decision-Making Tasks arXiv [paper] #competition #planning #training #self-improvement
[2025/06] Automated Skill Discovery for Language Agents through Exploration and Iterative Feedback arXiv [paper] #crafter #self-improvement
[2025/06] OmniReflect: Discovering Transferable Constitutions for LLM agents via Neuro-Symbolic Reflections arXiv [paper] #text-adventure #planning #training #self-improvement
[2025/05] SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents NeurIPS 2025 poster [paper] #text-adventure #planning #training #self-improvement
[2025/02] TextGames: Learning to Self-Play Text-Based Puzzle Games via Language Model Reasoning. arXiv [paper] #text-adventure #self-improvement
[2024/12] Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy NeurIPS 2024 [paper][code] #communication #self-improvement
[2024/09] Better than Your Teacher: LLM Agents that learn from Privileged AI Feedback ICLR 2025 Poster [paper] #text-adventure #planning #training #self-improvement
[2024/06] Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement EMNLP 2024 [paper][code] #text-adventure #self-improvement
[2024/05] Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy NeurIPS 2024 poster [paper] #communication #planning #multi-agent #self-improvement
[2024/04] ReAct Meets ActRe: When Language Agents Enjoy Training Data Autonomy arXiv [paper] #text-adventure #planning #training #self-improvement
[2024/04] Self-playing Adversarial Language Game Enhances LLM Reasoning NeurIPS 2024 [paper][code] #communication #training #self-improvement
[2024/03] Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents ACL 2024 [paper][code] #text-adventure #training #self-improvement
[2024/03] ReAct Meets ActRe: Autonomous Annotation of Agent Trajectories for Contrastive Self-Training COLM [paper] #text-adventure #planning #training #self-improvement
[2024/03] StateFlow: Enhancing LLM Task-Solving through State-Driven Workflows COLM [paper] #text-adventure #planning #self-improvement
[2024/02] Soft Self-Consistency Improves Language Model Agents arXiv [paper][code] #text-adventure #self-improvement
[2024/02] Empowering Large Language Model Agents through Action Learning COLM [paper][code] #text-adventure #planning #self-improvement
[2023/10] Lyfe Agents: Generative agents for low-cost real-time social interactions arXiv [paper] #sim-social #memory #multi-agent #self-improvement
[2023/03] Reflexion: Language Agents with Verbal Reinforcement Learning NeurIPS 2023 [paper][code] #text-adventure #training #self-improvement

prompting

[2026/05] GAMBIT: A Three-Mode Benchmark for Adversarial Robustness in Multi-Agent LLM Collectives arXiv [paper] #competition #multi-agent #prompting
[2026/05] PokerSkill: LLMs Can Play Expert-Level Poker without Training or Solvers arXiv [paper][code] #competition #tool-use #prompting
[2026/04] DORA Explorer: Improving the Exploration Ability of LLMs Without Training arXiv [paper] #text-adventure #planning #prompting
[2026/03] GTO Wizard Benchmark arXiv [paper] #competition #planning #multi-agent #prompting
[2026/03] Reward Prediction with Factorized World States arXiv [paper] #text-adventure #planning #prompting
[2026/02] World Models for Policy Refinement in StarCraft II arXiv [paper] #competition #world-model #prompting
[2026/02] **To Move or Not to Move: Constraint-based Pla

Truncated — view the full README on GitHub.

computer-games

game-agent

large-language-models

llm-based-agent

survey

Similar repos

zjunlp/LLMAgentPapers

Must-read Papers on LLM Agents.

3,121

AGI-Edgerunners/LLM-Agents-Papers

A repo lists papers related to LLM based agent

2,347

Andrewzh112/Awesome-LLM-based-MultiAgents

js-lee-AI/awesome-llm-agent-papers

A curated, continuously updated reading list of 200+ papers on LLM agents: planning, memory, tool…

WooooDyy/LLM-Agent-Paper-List

The paper list of the 86-page SCIS cover paper "The Rise and Potential of Large Language Model…

8,220

taichengguo/LLM_MultiAgents_Survey_Papers

Large Language Model based Multi-Agents: A Survey of Progress and Challenges (In IJCAI 2024)

1,319

hyp1231/awesome-llm-powered-agent

Awesome things about LLM-powered agents. Papers / Repos / Blogs / ...

2,256

YsTvT/Awesome-Agentic-RL-Papers

107

Contributors

155 commits

3 commits

2 commits

1 commits

git-disl/awesome-LLM-game-agent-papers

README

A Survey on Large Language Model-Based Game Agents (ACM CSUR)

Browse by Genre

Browse by Mechanism

By Genre

minecraft

text-adventure

communication

competition

cooperation

sim-social

sim-embodied

sim-other

crafter

action

video-adventure

benchmark

other

By Mechanism

planning

memory

multi-agent

world-model

tool-use

training

self-improvement

prompting

Contributors

Similar repos

git-disl/awesome-LLM-game-agent-papers

README

A Survey on Large Language Model-Based Game Agents (ACM CSUR)

Browse by Genre

Browse by Mechanism

By Genre

minecraft

text-adventure

communication

competition

cooperation

sim-social

sim-embodied

sim-other

crafter

action

video-adventure

benchmark

other

By Mechanism

planning

memory

multi-agent

world-model

tool-use

training

self-improvement

prompting

Similar repos

Contributors