📢 Updates

• 2025/12/30 We have updated 70 papers in the paper list, and the v2 paper is on its way!
• 2025/12/29 The first version of our paper is available on Arxiv.
• 2025/11/27 We created this reading list repository.

This reading list will be updated periodically, and if you have any suggestions or find some we missed, feel free to contact us! You can submit an issue or send an email (jfliang@ir.hit.edu.cn, haoli@ir.hit.edu.cn, cli@ir.hit.edu.cn, sxjiang@ir.hit.edu.cn).

🗂️ Tables of Contents

😄You can review the overall content flow of our paper here! Table Content

💾 Paper List

😊 We will continue to update with more papers!

Memory Categorization

• Episodic memory (Nature-based)
  • [2025/07] MapAgent: Trajectory-Constructed Memory-Augmented Planning for Mobile Task Automation
  • [2025/12] Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
• Semantic memory (Nature-based)
  • [2025/04] Dynamic Cheatsheet: Test-Time Learning with Adaptive Memory
  • [2025/09] ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
• Inside-trail memory (Scope-based)
  • [2024/04] MemLLM: Finetuning LLMs to Use Explicit Read-Write Memory
  • [2025/06] MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents
• Cross-trail memory (Scope-based)
  • [2025/10] EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle
  • [2025/10] Training-Free Group Relative Policy Optimization

Memory Storage

• Context window (Location)
  • [2025/10] Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
  • [2025/10] DeepAgent: {A} General Reasoning Agent with Scalable Toolsets
• Memory Bank (Location)
  • [2025/03]In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents
  • [2025/07]Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving
• Text (Format)
  • [2024/08] HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model
  • [2025/10] Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
• Graph (Format)
  • [2025/04] Mem0: Building Production-Ready {AI} Agents with Scalable Long-Term Memory
  • [2025/06] G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
  • [2025/10] D-SMART: Enhancing {LLM} Dialogue Consistency via Dynamic Structured Memory And Reasoning Tree
  • [2025/08] Seeing, Listening, Remembering, and Reasoning: {A} Multimodal Agent with Long-Term Memory
• Parameters (Format)
  • [2024/06] DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
  • [2025/05] WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning
  • [2025/08] SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experience
• Latent Representation (Format)
  • [2023/07] In-context Autoencoder for Context Compression in a Large Language Model
  • [2024/02] MEMORYLLM: Towards Self-Updatable Large Language Models
  • [2024/06] Language is primarily a tool for communication rather than thought
  • [2024/11] Explicit Memory Learning with Expectation Maximization
  • [2024/12] An Enhanced Text Compression Approach Using Transformer-based Language Models
  • [2024/12] Training Large Language Models to Reason in a Continuous Latent Space
  • [2025/02] M+: Extending MemoryLLM with Scalable Long-Term Memory
  • [2025/02] R3Mem: Bridging Memory Retention and Retrieval via Reversible Compression
  • [2025/10] CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension

Memory Management

• Flat Extraction (Extraction)
  • [2023/10] MemGPT: Towards LLMs as Operating Systems
  • [2025/10] TALM: Dynamic Tree-Structured Multi-Agent Framework with Long-Term Memory for Scalable Code Generation
  • [2025/10] MGA: Memory-Driven {GUI} Agent for Observation-Centric Interaction
• Hierarchical Extraction (Extraction)
  • [2024/02] A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts
  • [2025/02] A-MEM: Agentic Memory for {LLM} Agents
  • [2025/06] PersonaAgent: When Large Language Model Agents Meet Personalization at Test Time
  • [2025/09] H2R: Hierarchical Hindsight Reflection for Multi-Task {LLM} Agents
  • [2025/10] MemWeaver: A Hierarchical Memory from Textual Interactive Behaviors for Personalized Generation
  • [2025/10] Learning from Supervision with Semantic and Episodic Memory: {A} Reflective Approach to Agent Adaptation
  • [2025/10] Improving Code Localization with Repository Memory
  • [2025/10] LEGOMem: Modular Procedural Memory for Multi-agent {LLM} Systems for Workflow Automation
  • [2025/10] Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks
• Generative Extraction (Extraction)
  • [2025/09] ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
  • [2025/10] Scaling Long-Horizon LLM Agent via Context-Folding
  • [2025/10] AgentFold: Long-Horizon Web Agents with Proactive Context Management
• Inside-Trial Update (Update)
  • [2025/07] MemAgent: Reshaping Long-Context {LLM} with Multi-Conv RL-based Memory Agent
  • [2025/07] MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in {LLM} Agent Multi-Turn Conversations
  • [2025/09] SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents
• Cross-Trial Update (Update)
  • [2023/11] Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory
  • [2024/03] Ever-Evolving Memory by Blending and Refining the Past
  • [2025/08] Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
  • [2025/09] Mem-{(\alpha)}: Learning Memory Construction via Reinforcement Learning
  • [2024/09] SAGE: Self-evolving Agents with Reflective and Memory-augmented Abilities
  • [2025/09] MOOM: Maintenance, Organization and Optimization of Memory in Ultra-Long Role-Playing Dialogues
  • [2025/10] LLM Agents Beyond Utility: An Open-Ended Perspective
  • [2025/10] LightMem: Lightweight and Efficient Memory-Augmented Generation
  • [2025/11] FLEX: Continuous Agent Evolution via Forward Learning from Experience
• Similarity-based Retrieval (Retrieval)
  • [2025/11] LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning
  • [2025/11] A Benchmark for Procedural Memory Retrieval in Language Agents
• Multi-factor Retrieval (Retrieval)
  • [2023/04] Generative Agents: Interactive Simulacra of Human Behavior
  • [2025/05] From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents
  • [2025/07] Hierarchical Memory for High-Efficiency Long-Term Reasoning in {LLM} Agents
  • [2025/08] RCR-Router: Efficient Role-Aware Context Routing for Multi-Agent {LLM} Systems with Structured Memory
  • [2025/08] Memento: Fine-tuning LLM Agents without Fine-tuning LLMs
  • [2025/10] MemoCue: Empowering LLM-Based Agents for Human Memory Recall via Strategy-Guided Querying
• Contextual Augmentation (Application)
  • [2025/11] General Agentic Memory Via Deep Research
  • [2025/12] WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning
• Parameter Internalization(Application)
  • [2024/11] WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning
  • [2025/10] Agent Learning via Early Experience
  • [2025/12] MemVerse: Multimodal Memory for Lifelong Learning Agents

Star History

📖 Citation

If you find this repository useful in your research, a citation to our paper would be greatly appreciated:

@misc{liang2025aimeetsbrainmemory,
      title={AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents}, 
      author={Jiafeng Liang and Hao Li and Chang Li and Jiaqi Zhou and Shixin Jiang and Zekun Wang and Changkai Ji and Zhihao Zhu and Runxuan Liu and Tao Ren and Jinlan Fu and See-Kiong Ng and Xia Liang and Ming Liu and Bing Qin},
      year={2025},
      eprint={2512.23343},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2512.23343}, 
}