mlsanityData to 7 Oct 2026

From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms

arXiv 2605.06716 ↗First posted 7 May 2026cs.AI cs.CLcited by 19

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

Abstract (arXiv)

Large Language Model (LLM)-based agents have fundamentally reshaped artificial intelligence by integrating external tools and planning capabilities. While memory mechanisms have emerged as the architectural cornerstone of these systems, current research remains fragmented, oscillating between operating system engineering and cognitive science. This theoretical divide prevents a unified view of technological synthesis and a coherent evolutionary perspective. To bridge this gap, this survey proposes a novel evolutionary framework for LLM agent memory mechanisms, formalizing the development process into three stages: Storage (trajectory preservation), Reflection (trajectory refinement), and Experience (trajectory abstraction). We first formally define these three stages before analyzing the three core drivers of this evolution: the necessity for long-range consistency, the challenges in dynamic environments, and the ultimate goal of continual learning. Furthermore, we specifically explore two transformative mechanisms in the frontier Experience stage: proactive exploration and cross-trajectory abstraction. By synthesizing these disparate views, this work offers robust design principles and a clear roadmap for the development of next-generation LLM agents.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 173 of its 217 references that are in the map. First posted on arXiv 7 May 2026.

Builds on

173 of 217 references.

Closest ancestors · 41

Same direction, newest first

  1. 2026Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization26 Feb
  2. 2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents2 Feb
  3. 2025MemR3: Memory Retrieval via Reflective Reasoning for LLM Agents23 Dec
  4. 2025Learning Hierarchical Procedural Memory for LLM Agents through Bayesian Selection and Contrastive Refinement22 Dec
  5. 2025MemEvolve: Meta-Evolution of Agent Memory Systems21 Dec
  6. 2025From Personalization to Prejudice: Bias and Discrimination in Memory-Enhanced AI Agents for Recruitment18 Dec
  7. 2025Forgetful but Faithful: A Cognitive Memory Architecture and Benchmark for Privacy-Aware Generative Agents14 Dec
  8. 2025TeleMem: Building Long-Term and Multimodal Memory for Agentic AI12 Dec
  9. 2025Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution11 Dec
  10. 2025Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory25 Nov
  11. 2025O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents17 Nov
  12. 2025AgentFold: Long-Horizon Web Agents with Proactive Context Management28 Oct
29 more
  1. 2025Learning from Supervision with Semantic and Episodic Memory: A Reflective Approach to Agent Adaptation22 Oct
  2. 2025Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks14 Oct
  3. 2025Scaling Long-Horizon LLM Agent via Context-Folding13 Oct
  4. 2025Preference-Aware Memory Update for Long-Term LLM Agents10 Oct
  5. 2025Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles9 Oct
  6. 2025ToolMem: Enhancing Multimodal Agents with Learnable Tool Capability Memory8 Oct
  7. 2025CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension7 Oct
  8. 2025LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation6 Oct
  9. 2025Constructing coherent spatial memory in LLM agents through graph rectification5 Oct
  10. 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agents29 Sep
  11. 2025Coarse-to-Fine Grounded Memory for LLM Agent Planning21 Aug
  12. 2025Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Information18 Aug
  13. 2025Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory12 Aug
  14. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving8 Jul
  15. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions7 Jul
  16. 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents18 Jun
  17. 2025Contextual Experience Replay for Self-Improvement of Language Agents7 Jun
  18. 2025Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control23 May
  19. 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior21 May
  20. 2025LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners17 May
  21. 2025MemEngine: A Unified and Modular Library for Developing Advanced Memory of LLM-based Agents4 May
  22. 2025MemInsight: Autonomous Memory Augmentation for LLM Agents27 Mar
  23. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  24. 2025Memento No More: Coaching AI Agents to Master Multiple Tasks via Hints Internalization3 Feb
  25. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memory20 Jan
  26. 2024AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents5 Jul
  27. 2024A Survey on the Memory Mechanism of Large Language Model based Agents21 Apr
  28. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb
  29. 2024InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory7 Feb

Other references · 132

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  5. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  6. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  7. 2023Efficient Streaming Language Models with Attention Sinkscited by 2,115
  8. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  9. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  10. 2023LongBench: A Bilingual, Multitask Benchmark for Long Context Understandingcited by 1,378
  11. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  12. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,270
38 more
  1. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  2. 2024Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inferencecited by 487
  3. 2025Group-in-Group Policy Optimization for LLM Agent Trainingcited by 442
  4. 2025Multi-Agent Collaboration Mechanisms: A Survey of LLMscited by 424
  5. 2024Understanding the planning of LLM agents: A surveycited by 414
  6. 2024LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitaskscited by 367
  7. 2025RAGEN: Understanding Self-Evolution in LLM Agents via Multi-Turn Reinforcement Learningcited by 357
  8. 2024VideoAgent: Long-form Video Understanding with Large Language Model as Agentcited by 323
  9. 2023How Language Model Hallucinations Can Snowballcited by 310
  10. 2024Titans: Learning to Memorize at Test Timecited by 303
  11. 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learningcited by 252
  12. 2024WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learningcited by 243
  13. 2022RealTime QA: What's the Answer Right Now?cited by 239
  14. 2021Mind the Gap: Assessing Temporal Generalization in Neural Language Modelscited by 226
  15. 2024MA-LMM: Memory-Augmented Large Multimodal Model for Long-Term Video Understandingcited by 223
  16. 2024BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystackcited by 211
  17. 2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Taskscited by 166
  18. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 163
  19. 2025WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learningcited by 162
  20. 2026Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skillscited by 161
  21. 2025Dynamic Cheatsheet: Test-Time Learning with Adaptive Memorycited by 146
  22. 2025Do LLMs Recognize Your Preferences? Evaluating Personalized Preference Following in LLMscited by 142
  23. 2023ChatDB: Augmenting LLMs with Databases as Their Symbolic Memorycited by 136
  24. 2024LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuningcited by 133
  25. 2025EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecyclecited by 129
  26. 2024AgentScope: A Flexible yet Robust Multi-Agent Platformcited by 120
  27. 2025From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMscited by 119
  28. 2025Where LLM Agents Fail and How They can Learn From Failurescited by 118
  29. 2022TemporalWiki: A Lifelong Benchmark for Training and Evaluating Ever-Evolving Language Modelscited by 117
  30. 2025Inducing Programmatic Skills for Agentic Taskscited by 103
  31. 2024WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environmentcited by 99
  32. 2023MemoChat: Tuning LLMs to Use Memos for Consistent Long-Range Open-Domain Conversationcited by 94
  33. 2025Agent Lightning: Train ANY AI Agents with Reinforcement Learningcited by 94
  34. 2025VerlTool: Towards Holistic Agentic Reinforcement Learning with Tool Usecited by 92
  35. 2021Time Waits for No One! Analysis and Challenges of Temporal Misalignmentcited by 91
  36. 2025Reinforcement Learning for Self-Improving Agent with Skill Librarycited by 91
  37. 2025MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Serverscited by 89
  38. 2023CLIN: A Continually Learning Language Agent for Rapid Task Adaptation and Generalizationcited by 88

50 most cited of 132 All 132 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 19.

19 papers.

Sort:

By area:

  1. 2026MemTxn: A Transaction Boundary for Source-Supported Updates and Complete-State Recovery in Agent Memorycited by 5
  2. 2026Rethinking Continual Experience Internalization for Self-Evolving LLM Agentscited by 4
  3. 2026AdaMEM: Test-Time Adaptive Memory for Language Agentscited by 4
  4. 2026TriggerBench: Investigating Prospective Memory for Large Language Modelscited by 4
  5. 2026Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memorycited by 3
  6. 2026Memory for Large Language Modelscited by 2
  7. 2026MESA:Task-Adaptive Multi-Structure Evidence Selection for Long-Horizon Agent Memorycited by 1
  8. 2026Reflect, Revise, Reuse: Training-Free Skill Evolution for GUI Agentscited by 1
  9. 2026MemTools: A Unified Research Framework for Interoperable Agent Memorycited by 0
  10. 2026Continual Learning in Transitioncited by 0
  11. 2026What Makes Agent Memory Useful for Reliable Unanswerable Question Handling?cited by 0
  12. 2026Inferring Hidden User Models from the Behavior of Personalized LLM Agentscited by 0
7 more
  1. 2026Graph-Based Personalized Memory for LLM Agents: Representation, Evolution, Retrieval, and Evaluationcited by 0
  2. 2026STRETCH the Boundaries: A Unified Self-Taught Framework for Progressive LLM Evolutioncited by 0
  3. 2026MemCalib: Benchmarking and Optimizing Memory Use in LLM Agentscited by 0
  4. 2026Just-in-Time Memory: Learning to Curate Task-Adaptive Memory for LLM Agentscited by 0
  5. 2026Amnesia by Design, Memory By Necessity: Persistent State for Document Intelligencecited by 0
  6. 2026Beyond Dyadic Memory: Interaction-Aware Multimodal Memory with Adaptive Agentic Retrieval for Multi-Party Spoken Conversationscited by 0
  7. 2026ATTUNER: Recomputation-Free KV Cache Reuse via Query-Side Adaptationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
  2. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework
  3. 2026GenericAgent: A Token-Efficient Self-Evolving LLM Agent via Contextual Information Density Maximization (V1.0)
  4. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents
  5. 2026Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
  6. 2026Exploring Cross-Scenario Generality of Agentic Memory Systems: Diagnostics and a Strong Baseline
  7. 2026Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads
  8. 2026Learning What to Remember and What to Internalize in LLM Self-Evolution via Adaptive Memory-Parameter Coordination