mlsanityData to 14 Oct 2026

A-MEM: Agentic Memory for LLM Agents

arXiv 2502.12110 ↗First posted 17 Feb 2025cs.CL cs.HCcited by 1,063

On the map: LLM agents and tool use → Agent memory systems

Abstract (arXiv)

While large language model (LLM) agents can effectively use external tools for complex real-world tasks, they require memory systems to leverage historical experiences. Current memory systems enable basic storage and retrieval but lack sophisticated memory organization, despite recent attempts to incorporate graph databases. Moreover, these systems' fixed operations and structures limit their adaptability across diverse tasks. To address this limitation, this paper proposes a novel agentic memory system for LLM agents that can dynamically organize memories in an agentic way. Following the basic principles of the Zettelkasten method, we designed our memory system to create interconnected knowledge networks through dynamic indexing and linking. When a new memory is added, we generate a comprehensive note containing multiple structured attributes, including contextual descriptions, keywords, and tags. The system then analyzes historical memories to identify relevant connections, establishing links where meaningful similarities exist. Additionally, this process enables memory evolution - as new memories are integrated, they can trigger updates to the contextual representations and attributes of existing historical memories, allowing the memory network to continuously refine its understanding. Our approach combines the structured organization principles of Zettelkasten with the flexibility of agent-driven decision making, allowing for more adaptive and context-aware memory management. Empirical experiments on six foundation models show superior improvement against existing SOTA baselines. The source code for evaluating performance is available at https://github.com/WujiangXu/A-mem, while the source code of the agentic memory system is available at https://github.com/WujiangXu/A-mem-sys.

Key facts. Cited by 1,063 papers in the map (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 34 of its 50 references that are in the map. First posted on arXiv 17 Feb 2025.

Builds on

34 of 50 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb
  2. 2024A Human-Inspired Reading Agent with Gist Memory of Very Long Contexts15 Feb

Other references · 32

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  5. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  6. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  7. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  8. 2021Improving language models by retrieving from trillions of tokenscited by 1,293
  9. 2023Mind2Web: Towards a Generalist Agent for the Webcited by 1,242
  10. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 1,002
  11. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  12. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
20 more
  1. 2023Active Retrieval Augmented Generationcited by 516
  2. 2023Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergycited by 346
  3. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 267
  4. 2023RA-DIT: Retrieval-Augmented Dual Instruction Tuningcited by 195
  5. 2023Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Modelscited by 184
  6. 2024The Impact of Reasoning Step Length on Large Language Modelscited by 153
  7. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systemscited by 141
  8. 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networkscited by 119
  9. 2023SCM: Enhancing Large Language Model with Self-Controlled Memory Frameworkcited by 98
  10. 2024AIOS: LLM Agent Operating Systemcited by 97
  11. 2023Learning to Filter Context for Retrieval-Augmented Generationcited by 83
  12. 2023Augmentation-Adapted Retriever Improves Generalization of Language Models as Generic Plug-Incited by 71
  13. 2023RET-LLM: Towards a General Read-Write Memory for Large Language Modelscited by 64
  14. 2024AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent Systemcited by 53
  15. 2023Conversation Chronicles: Towards Diverse Temporal and Relational Dynamics in Multi-Session Conversationscited by 47
  16. 2023Rethinking Cross-Domain Sequential Recommendation under Open-World Assumptionscited by 20
  17. 2024DialSim: A Dialogue Simulator for Evaluating Long-Term Multi-Party Dialogue Understanding of Conversational Agentscited by 20
  18. 2024From Commands to Prompts: LLM-based Semantic File System for AIOScited by 14
  19. 2023Neural Node Matching for Multi-Target Cross Domain Recommendationcited by 8
  20. 2024GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruningcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 159; 2026: 904.

1,063 papers.

Sort:

By area:

  1. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 779
  2. 2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Modelscited by 398
  3. 2025Memory in the Age of AI Agentscited by 303
  4. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 284
  5. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactionscited by 254
  6. 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agentscited by 238
  7. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learningcited by 237
  8. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 205
  9. 2025Survey on Evaluation of LLM-based Agentscited by 204
  10. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 180
  11. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 180
  12. 2025MIRIX: Multi-Agent Memory System for LLM-Based Agentscited by 173
38 more
  1. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 170
  2. 2025AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challengescited by 169
  3. 2025Memory OS of AI Agentcited by 150
  4. 2026SimpleMem: Efficient Lifelong Memory for LLM Agentscited by 149
  5. 2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agentscited by 142
  6. 2025ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarizationcited by 141
  7. 2025MemOS: A Memory OS for AI Systemcited by 138
  8. 2025ACON: Optimizing Context Compression for Long-horizon LLM Agentscited by 136
  9. 2025Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memorycited by 136
  10. 2026MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memorycited by 129
  11. 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMscited by 127
  12. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  13. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  14. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systemscited by 122
  15. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 116
  16. 2026AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolutioncited by 115
  17. 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agentscited by 109
  18. 2025Memp: Exploring Agent Procedural Memorycited by 103
  19. 2025AgentFold: Long-Horizon Web Agents with Proactive Context Managementcited by 103
  20. 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behaviorcited by 101
  21. 2025Towards Scientific Intelligence: A Survey of LLM-based Scientific Agentscited by 98
  22. 2025Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memorycited by 97
  23. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 94
  24. 2026OpenClaw-RL: Train Any Agent Simply by Talkingcited by 90
  25. 2025PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memorycited by 88
  26. 2025MemInsight: Autonomous Memory Augmentation for LLM Agentscited by 85
  27. 2026Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agentscited by 78
  28. 2025From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discoverycited by 77
  29. 2026Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineeringcited by 74
  30. 2025Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolutioncited by 73
  31. 2025MemoryGraft: Persistent Compromise of LLM Agents via Poisoned Experience Retrievalcited by 72
  32. 2025Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agentscited by 62
  33. 2025A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challengescited by 62
  34. 2025MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systemscited by 61
  35. 2025Mem-α: Learning Memory Construction via Reinforcement Learningcited by 55
  36. 2026Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agentscited by 54
  37. 2026MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agentscited by 52
  38. 2025Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Managementcited by 51

50 most cited of 1,063 All 1,063 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
  2. 2024On the Structural Memory of LLM Agents
  3. 2024A Survey on the Memory Mechanism of Large Language Model based Agents
  4. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
  5. 2026Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and Evaluation
  6. 2026Agent Zero Memory: Provenance-Aware Long-Term Memory for LLM Agents
  7. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applications
  8. 2026Are We Ready For An Agent-Native Memory System?