A curated collection of research papers and resources on memory mechanisms in Large Language Model (LLM) agents
π Papers β’ π€ Contributing β’ π License
Out of personal interest and learning needs, this repository is dedicated to collecting and organizing research work related to memory mechanisms in LLM agents. The goal is to provide a comprehensive resource for researchers, practitioners, and enthusiasts in the AI community who are interested in understanding how memory systems enhance the capabilities of language model-based agents.
- π Curate high-quality research papers on agent memory systems
- π Track the latest developments in LLM agent memory mechanisms
- π Share knowledge and resources with the AI research community
- π‘ Facilitate learning and exploration in this emerging field
- 2024-04-21 A Survey on the Memory Mechanism of Large Language Model based Agents
- 2025-05-27 Rethinking Memory in AI: Taxonomy, Operations, Topics, and Future Directions
- 2025-12-15 Memory in the Age of AI Agents: A Survey
- 2025-07-07 Towards General Continuous Memory for Vision-Language Models
- 2025-10-09 Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
- 2025-11-14 VisMem: Latent Vision Memory Unlocks Potential of Vision-Language Models
- 2025-12-03 MemVerse: Multimodal Memory for Lifelong Learning Agents
- 2023-05-21 MemoryBank: Enhancing Large Language Models with Long-Term Memory retrieval-based
- 2023-08-20 ExpeL: LLM Agents Are Experiential Learners retrieval-based, task-level
- 2024-05-26 MEMORYLLM: Towards Self-Updatable Large Language Models
- 2024-09-11 Agent Workflow Memory retrieval-based, high-level experiences
- 2025-02-01 M+: Extending MemoryLLM with Scalable Long-Term Memory latent memory
- 2025-02-17 A-MEM: Agentic Memory for LLM Agents
- 2025-04-09 MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentation
- 2025-04-09 SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills condensed skills - reusable APIs
- 2025-04-28 Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
- 2025-06-16 G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems retrieval-based, raw trajetcory, task-level
- 2025-06-18 MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents RL, long-context inputs
- 2025-06-27 Parametric Retrieval Augmented Generation
- 2025-07-03 MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agent RL, long-context inputs
- 2025-07-08 Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving retrieval-based, step-level, cross-domain
- 2025-07-10 MIRIX: Multi-Agent Memory System for LLM-Based Agents
- 2025-08-05 MemOS: A Memory OS for AI System
- 2025-08-08 Memp: Exploring agent procedural memory retrieval-based, high-level experiences
- 2025-09-19 Latent learning: episodic memory complements parametric learning by enabling flexible reuse of experiences
- 2025-09-27 Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents
- 2025-09-30 Mem-Ξ±: Learning Memory Construction via Reinforcement Learning
- 2025-10-08 Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning
- 2025-10-12 MemGen: Weaving Generative Latent Memory for Self-Evolving Agents latent, memory evolving
- 2025-10-09 Learning on the Job: An Experience-Driven, Self-Evolving Agent for Long-Horizon Tasks
- 2025-10-10 Preference-Aware Memory Update for Long-Term LLM Agents personalized memoryοΌre-promptοΌ
- 2025-10-14 Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
- 2025-10-20 MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systems
- 2025-10-21 LightMem: Lightweight and Efficient Memory-Augmented Generation
Coming soon...
Contributions are welcome! If you know of any important papers or resources related to memory in LLM agents that should be included, please feel free to:
- π΄ Fork the repository
- β¨ Add your contributions
- π¬ Submit a pull request
Or simply open an issue with suggestions!
This repository is maintained for educational and research purposes. Please refer to individual papers for their respective licenses and citation information.
If you find this repository helpful, please consider giving it a star! β
Made with β€οΈ for the AI Research Community