Awesome Agent

This repo collects papers and repositories about agent. Especially, we focus on the agent that can be applied to the real-world tasks, such as robotics, search engine, scientific discovery, etc. Please feel free to PR the works missed by the repo. We use the following format to record the papers:

[Paper Title](paper link), Conference/Journal, Year, Team | [code](code link), [project](project link)

Table of Contents

• Awesome Agent
  • Table of Contents
    • Foundation Model (LLM, VLM, etc.)
    • Robotics
    • Scientific Discovery
    • Multi-Agent
    • Decision-Making
    • Others
  • Datasets and Benchmarks
    • General AI Agent
    • Robotics
  • Other Resources
    • Github Collections
    • Tutorial & Course & Blog
    • Group
    • Frameworks
      • Foundation Models
      • Multi-Agent
    • Links
    • Star History

Foundation Model (LLM, VLM, etc.)

2025

• R1-V: Reinforcing Super Generalization Ability in Vision Language Models with Less Than $3, Blog, 2025.2 | code
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning, Preprint, 2025.1, DeepSeek | code

2024

• DeepSeek-V3 Technical Report, Preprint, 2024.12, DeepSeek | code
• LLaVA-OneVision: Easy Visual Task Transfer, ArXiv, 2024.8, NTU & Bytedance | project, code
• VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generation, ArXiv, 2024.9, THU & MIT & NVIDIA & UCB & UCSD. | project, code
• Qwen2 & QwQ: Reflect Deeply on the Boundaries of the Unknown, ArXiv, 2024.7 & 2024.11, Qwen Team at Alibaba | model, project, blog
• Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions, ArXiv, 2024.11, AIDC-AI at Alibaba | model, code
• O1 Journey: O1 Replication Journey – Part 2: Surpassing O1-preview through Simple Distillation Big Progress or Bitter Lesson?, ArXiv, 2024.11, GAIR SJTU | code
• Gemma: Open models based on gemini research and technology, ArXiv, 2024.3, Google | project
• Minicpm: Unveiling the potential of small language models with scalable training strategies, CoLM, 2024, OpenBMB. | blog, code
• MiniCPM-V: A GPT-4V Level MLLM on Your Phone, ArXiv, 2024, OpenBMB. | code

2023

• ReAct: Synergizing Reasoning and Acting in Language Models, ICLR, 2023, Princeton & Google | project, code

Robotics

Conference Collections

• RSS2025
• RSS2024
• CoRL2024
• ICRA2024
• IROS2024

2025

2024

• AgiBot World, Zhiyuan Robot | dataset, code
• Genesis: A Generative and Universal Physics Engine for Robotics and Beyond, ArXiv, 2024. | code, project
• Grounding Large Language Models in Interactive Environments with Online Reinforcement Learning, ICML, 2024, Inria. | code
• True Knowledge Comes from Practice: Aligning LLMs with Embodied Environments via Reinforcement Learning, ICLR2024, NTU. | code
• Octopi: Object Property Reasoning with Large Tactile-Language Models, RSS, 2024
• 3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations, RSS, 2024
• Learning Multi-Agent Collaborative Manipulation for Long-Horizon Quadrupedal Pushing, ArXiv, 2024, CMU & Google. | project, code
• ARMOR：Egocentric Perception for Humanoid Robot Collision Avoidance and Motion Planning, ArXiv, 2024.12. CMU & Apple
• CASHER: Robot Learning with Super-Linear Scaling, ArXiv, 2024.12. MIT & UoW | project
• CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation, ArXiv, 2024.12, MSRA Asia | project, code
• Vision-Language Foundation Models as Effective Robot Imitators, ICLR, 2024, Bytedance | project, code
• DeeR-VLA: Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution, ArXiv, 2024.11, Tsinghua & Bytedance | code
• π0: A Vision-Language-Action Flow Model for General Robot Control, ArXiv, 2024.10, Physical Intelligence | project, code
• GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation, ArXiv, 2024.10, Bytedance | project
• Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers, ArXiv, 2024.9, MIT | code
• Mobile ALOHA Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation, CoRL, 2024, Stanford | project, code, code2
• OpenVLA: An Open-Source Vision-Language-Action Model, ArXiv, 2024.6, Stanford | project, code
• RoboUniView: Visual-Language Model with Unified View Representation for Robotic Manipulation, ArXiv, 2024.6, Meituan | project, code
• RoboDreamer: Learning Compositional World Models for Robot Imagination, ArXiv, 2024.4, HKUST & MIT & UCSD & Google Research | project
• RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches, ICLR, 2024, Google DeepMind | project
• ALOHA Unleashed 🌋: A Simple Recipe for Robot Dexterity, ArXiv, 2024, Google DeepMind | project
• HumanPlus Humanoid Shadowing and Imitation from Humans, CoRL, 2024, Stanford | project, code
• Universal Manipulation Interface In-The-Wild Robot Teaching Without In-The-Wild Robots, RSS, 2024, Stanford & Columbia | project, code
• 3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations, RSS, 2024, Shanghai Qizhi Institute & SJTU & Tsinghua & Shanghai AI Lab | project, code
• RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation, ArXiv, 2024, Tsinghua | project
• Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goals, RSS, 2024, KIT | project, code
• Octo: An Open-Source Generalist Robot Policy, ArXiv, 2024, UCB & Stanford & CMU & Google DeepMind | project, code
• Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks, ICLR, 2024, Harvard | project, code
• UniSim: Learning Interactive Real-World Simulators, ICLR, 2024, UCB & Google DeepMind & MIT | project

2023

• GR-1: Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation, ArXiv, 2023.12, Bytedance | project, code
• RT-2: Robotics Transformer for Real-World Control at Scale, CoRL, 2023, Google DeepMind |project
• Open X-Embodiment: Robotic Learning Datasets and RT-X Models, CoRL Workshop, 2023, Open X-Embodiment Collaboration | project, code
• VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Models, CoRL, 2023, Stanford | project, code
• Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware, RSS, 2023, Stanford | project, code
• Diffusion Policy: Visuomotor Policy Learning via Action Diffusion, RSS2023 & IJRR2024, Columbia | project, code
• HULC++: Grounding Language with Visual Affordances over Unstructured Data, ICRA, 2023, University of Freiburg | project, code
• Learning Universal Policies via Text-Guided Video Generation, NeurIPS, 2023, MIT & Google Brain | project, unofficial code
• Learning to Act from Actionless Videos through Dense Correspondences, ArXiv, 2023, National Taiwan University | project, code
• RT-1: Robotics Transformer for Real-World Control at Scale, RSS, 2023, Google Robotics | code, project

2022

• Do As I Can, Not As I Say: Grounding Language in Robotic Affordances, CoRL, 2022, Google Robotics | code, project

Scientific Discovery

2024

• Agent Laboratory: Using LLM Agents as Research Assistants, ArXiv, 2025.1, AMD & JHU | project, code

Multi-Agent

2025

• MCP | code
• Do as We Do, Not as You Think: the Conformity of Large Language Models, ICLR, 2025, ZJU | code

2024

• WiS Platform: Enhancing Evaluation of LLM-Based Multi-Agent Systems Through Game-Based Analysis, ArXiv, 2024.12, Alibaba. | project
• Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks, ArXiv, 2024, Microsoft. | blog, code
• SMoA: Improving Multi-agent Large Language Models with Sparse Mixture-of-Agents, ArXiv, 2024, ASU & MSU & KAUST & UT Austin. | code
• Mixture-of-Agents Enhances Large Language Model Capabilities, ArXiv, 2024. 6, Together AI. | code
• AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors, ICLR, 2024. THU & BUPT & Tecent | code
• Metagpt: Meta programming for multi-agent collaborative framework, ICLR, 2024. DeepWisdom & KAUST & XMU & CUHKSZ & NJU & UoPenn & UCB | code
• ChatDev: Communicative Agents for Software Development, ACL, 2024. THU & BUPT & DUT etc. | code
• Cybench: A Framework for Evaluating Cybersecurity Capabilities and Risk of Language Models, ArXiv, 2024.8 | project, code
• Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows, ArXiv, 2024.11, HKU & Salesforce & Google Deepmind etc. | project, code
• Conformity in Large Language Models, ArXiv, 2024.10, Cambridge
• Internet of Agents: Weaving a Web of Heterogeneous Agents for Collaborative Intelligence, ArXiv, 2024.7, THU & PKU & BUPT & Tencent | project, code

2023

• AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation, ArXiv, 2023. MS & PSU & UoW | code
• CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society, NeurIPS, 2023, KAUST. | project, code

2022

• Diversity is All You Need: Learning Skills without a Reward Function, ICLR, 2019, CMU & UCB & Google. | project, code
• Multi-Agent Reinforcement Learning is A Sequence Modeling Problem, NeurIPS, 2022, SJTU | project, code
• Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning, ICLR, 2022, Oxford etc.

Before 2020

• On the Control of Multi-Agent Systems: A Survey, Foundations and Trends©R in Systems and Control, 2019, Northeastern University China.
• A actor-based architecture for customizing and controlling agent ensembles, IEEE Intelligent Systems and their Applications, 1999, UIUC.
• KQML as an agent communication language, CIKM, 1994.

Decision-Making

2025

• Think Twice, Act Once: A Co-Evolution Framework of LLM and RL for Large-Scale Decision Making, ICML, 2025, ZJU & PKU.

Others

2024

• Haisor: Human-aware Indoor Scene Optimization via Deep Reinforcement Learning, ACM ToG, 2024, NVIDIA. | project

2021

• 3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics, ICCV, 2021, Alibaba & CAS & SFU. | project, code
• Multi Agent Reinforcement Learning of 3D Furniture Layout Simulation in Indoor Graphics Scenes, ICLR SimDL Workshop, 2021, Longfor & IBM. | code(partial)

Datasets and Benchmarks

General AI Agent

• Gaia: a benchmark for general ai assistants, ICLR, 2024, Meta | code, leadboard

Robotics

• DROID: A Large-Scale In-the-Wild Robot Manipulation Dataset, ArXiv, 2024.3, DROID Dataset Team | project
• RLBench, RA-L, 2020, ICL | project, code
• CALVIN, RA-L, 2022,University of Freiburg | project, code
• ManiSkill 1&2&3, ICLR, 2023, UCSD | project, code

Other Resources

Github Collections

• Awesome AGI Agents
• Awesome Agents
• Awesome AI Agents
• Awesome AI Agents
• Awesome LLM Powered Agent
• Awesome AI Agents
• Embodied_AI_Paper_List
• Awesome-Multimodal-Large-Language-Models
• Awesome-LLM
• diffusion-literature-for-robotics

Tutorial & Course & Blog

• LLM Powered Autonomous Agents, Blog, 2023.6, Lilian Weng
• The Second Half, Blog, 2025.4, Shunyu Yao
• Why We Think, Blog, 2025.5, Lilian Weng
• CMU 16-782 Planning and Decision-making in Robotics, Notes, 2024
• AI4OPT Seminar Series: On the Foundations of Interactive Decision Making and Reinforcement Learning, Video, 2023
• Cornell CS6756 Learning for Robot Decision Making, Video, 2023
• NTU MLDS, Video, Slides, Notes, 2018
• Intro to Reinforcement Learning, Video, Video(Chinese), Notes, Notes(Chinese), 2015

Group

• OpenAI
• OpenBMB
• DeepSeek
• Huggingface LeRobot
• Physical Intelligence

Frameworks

Foundation Models

• Llama Series
• Gemma Series
• Qwen Series
• DeepSeek Series
• MiniMax Series
• Mistral Series
• Cosmos Series

Multi-Agent

• MCP | 中译版
• openr
• swarm
• autogen
• LlamaIndex
• LangChain
• AutoGPT
• AgentGPT
• MetaGPT
• Open Interpreter
• AgentVerse
• Crew AI
• LangGraph
• CAMEL

Links

• RSS2024
• RSS2025
• Papercopilot

Star History