mlsanityData to 7 Oct 2026

A Survey on the Memory Mechanism of Large Language Model based Agents

arXiv 2404.13501 ↗First posted 21 Apr 2024cs.AIcited by 622

On the map: World models → World models for language agents

also in 1 more
Abstract (arXiv)

Large language model (LLM) based agents have recently attracted much attention from the research and industry communities. Compared with original LLMs, LLM-based agents are featured in their self-evolving capability, which is the basis for solving real-world problems that need long-term and complex agent-environment interactions. The key component to support agent-environment interactions is the memory of the agents. While previous studies have proposed many promising memory mechanisms, they are scattered in different papers, and there lacks a systematical review to summarize and compare these works from a holistic perspective, failing to abstract common and effective designing patterns for inspiring future studies. To bridge this gap, in this paper, we propose a comprehensive survey on the memory mechanism of LLM-based agents. In specific, we first discuss ''what is'' and ''why do we need'' the memory in LLM-based agents. Then, we systematically review previous studies on how to design and evaluate the memory module. In addition, we also present many agent applications, where the memory module plays an important role. At last, we analyze the limitations of existing work and show important future directions. To keep up with the latest advances in this field, we create a repository at urlhttps://github.com/nuster1128/LLMAgentMemorySurvey.

Key facts. Cited by 622 papers in the map (data through 7 Oct 2026). Placed in World models for language agents, one of 11 directions in World models. Builds on 157 of its 231 references that are in the map. First posted on arXiv 21 Apr 2024.

Builds on

157 of 231 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agents27 Jul
  2. 2023Generative Agents: Interactive Simulacra of Human Behavior7 Apr
  3. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learning8 Oct

Other references · 154

  1. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  6. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  7. 2023A Survey of Large Language Modelscited by 2,537
  8. 2017Billion-scale similarity search with GPUscited by 2,477
  9. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  10. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  11. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  12. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
38 more
  1. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  2. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  3. 2023A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questionscited by 1,582
  4. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  5. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,378
  6. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  7. 2023A Survey on Evaluation of Large Language Modelscited by 1,227
  8. 2023A Survey on Multimodal Large Language Modelscited by 898
  9. 2022GLM-130B: An Open Bilingual Pre-trained Modelcited by 837
  10. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
  11. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 800
  12. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 752
  13. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 695
  14. 2023Bias and Fairness in Large Language Models: A Surveycited by 626
  15. 2023Instruction Tuning for Large Language Models: A Surveycited by 617
  16. 2021Editing Factual Knowledge in Language Modelscited by 548
  17. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 539
  18. 2022Using Large Language Models to Simulate Multiple Humans and Replicate Human Subject Studiescited by 506
  19. 2024Large Language Models: A Surveycited by 506
  20. 2021Fast Model Editing at Scalecited by 491
  21. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 457
  22. 2024Understanding the planning of LLM agents: A surveycited by 414
  23. 2023Harnessing the Power of LLMs in Practice: A Survey on ChatGPT and Beyondcited by 409
  24. 2023Augmented Language Models: a Surveycited by 398
  25. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
  26. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 380
  27. 2023Editing Large Language Models: Problems, Methods, and Opportunitiescited by 367
  28. 2023A Survey of Hallucination in Large Foundation Modelscited by 365
  29. 2023Character-LLM: A Trainable Agent for Role-Playingcited by 335
  30. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  31. 2023Explainability for Large Language Models: A Surveycited by 331
  32. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 326
  33. 2023Tool Learning with Foundation Modelscited by 302
  34. 2023Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memorycited by 288
  35. 2023A Survey on Multimodal Large Language Models for Autonomous Drivingcited by 288
  36. 2024CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challengescited by 278
  37. 2023ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solvingcited by 276
  38. 2021Beyond Goldfish Memory: Long-Term Open-Domain Conversationcited by 266

50 most cited of 154 All 154 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 58; 2025: 195; 2026: 369.

622 papers.

Sort:

By area:

  1. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 722
  2. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 424
  3. 2024Automated Design of Agentic Systemscited by 360
  4. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 253
  5. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 242
  6. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learningcited by 220
  7. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  8. 2025AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Societycited by 180
  9. 2024Large Language Model-Based Agents for Software Engineering: A Surveycited by 173
  10. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 163
  11. 2024Understanding World or Predicting Future? A Comprehensive Survey of World Modelscited by 161
  12. 2024Large Language Model-Brained GUI Agents: A Surveycited by 160
38 more
  1. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 155
  2. 2025From LLM Reasoning to Autonomous AI Agents: A Comprehensive Reviewcited by 146
  3. 2025Evaluation and Benchmarking of LLM Agents: A Surveycited by 145
  4. 2025Memory OS of AI Agentcited by 140
  5. 2025Memory Injection Attacks on LLM Agents via Query-Only Interactioncited by 127
  6. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  7. 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 122
  8. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  9. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systemscited by 112
  10. 2025A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deploymentcited by 110
  11. 2026AutoSkill: Experience-Driven Lifelong Learning via Skill Self-Evolutioncited by 105
  12. 2024HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Modelcited by 101
  13. 2025On Memory Construction and Retrieval for Personalized Conversational Agentscited by 101
  14. 2024AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agentscited by 100
  15. 2025Unveiling Privacy Risks in LLM Agent Memorycited by 99
  16. 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agentscited by 99
  17. 2025TRAIL: Trace Reasoning and Agentic Issue Localizationcited by 98
  18. 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behaviorcited by 95
  19. 2025A Survey on Trustworthy LLM Agents: Threats and Countermeasurescited by 93
  20. 2025Memp: Exploring Agent Procedural Memorycited by 88
  21. 2024A Survey of Large Language Models for Financial Applications: Progress, Prospects and Challengescited by 86
  22. 2025MemInsight: Autonomous Memory Augmentation for LLM Agentscited by 84
  23. 2024Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Taskscited by 83
  24. 2025MemBench: Towards More Comprehensive Evaluation on the Memory of LLM-based Agentscited by 82
  25. 2025PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memorycited by 82
  26. 2025MemEvolve: Meta-Evolution of Agent Memory Systemscited by 81
  27. 2025Lifelong Learning of Large Language Model based Agents: A Roadmapcited by 78
  28. 2024From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMscited by 77
  29. 2025A Survey of AI Agent Protocolscited by 77
  30. 2026Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agentscited by 72
  31. 2024Retrieval-Augmented Generation for Natural Language Processing: A Surveycited by 70
  32. 2025A Survey of Personalized Large Language Models: Progress and Future Directionscited by 65
  33. 2025Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolutioncited by 65
  34. 2024Direct Multi-Turn Preference Optimization for Language Agentscited by 63
  35. 2024Navigating the Risks: A Survey of Security, Privacy, and Ethics Threats in LLM-Based Agentscited by 63
  36. 2025Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agentscited by 60
  37. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontierscited by 60
  38. 2025LLM Agents for Education: Advances and Applicationscited by 59

50 most cited of 622 All 622 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions
  2. 2025A-MEM: Agentic Memory for LLM Agents
  3. 2026Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitations
  4. 2026EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective
  5. 2025From Language to Action: A Review of Large Language Models as Autonomous Agents and Tool Users
  6. 2026MemCo: Memory-Centric Collaboration for Generalizing LLM Agents to Unseen Environments
  7. 2026Toward Formalizing LLM-Based Agent Designs through Structural Context Modeling and Semantic Dynamics Analysis
  8. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applications