mlsanityData to 14 Oct 2026

From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs

arXiv 2504.15965 ↗First posted 22 Apr 2025cs.IRcited by 124

Not on the map. Why?

Cited by 66 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Memory is the process of encoding, storing, and retrieving information, allowing humans to retain experiences, knowledge, skills, and facts over time, and serving as the foundation for growth and effective interaction with the world. It plays a crucial role in shaping our identity, making decisions, learning from past experiences, building relationships, and adapting to changes. In the era of large language models (LLMs), memory refers to the ability of an AI system to retain, recall, and use information from past interactions to improve future responses and interactions. Although previous research and reviews have provided detailed descriptions of memory mechanisms, there is still a lack of a systematic review that summarizes and analyzes the relationship between the memory of LLM-driven AI systems and human memory, as well as how we can be inspired by human memory to construct more powerful memory systems. To achieve this, in this paper, we propose a comprehensive survey on the memory of LLM-driven AI systems. In particular, we first conduct a detailed analysis of the categories of human memory and relate them to the memory of AI systems. Second, we systematically organize existing memory-related work and propose a categorization method based on three dimensions (object, form, and time) and eight quadrants. Finally, we illustrate some open problems regarding the memory of current AI systems and outline possible future directions for memory in the era of large language models.

Key facts. Cited by 124 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Apr 2025.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 31; 2026: 93.

124 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 303
  2. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 205
  3. 2025Memory OS of AI Agentcited by 150
  4. 2025MemOS: A Memory OS for AI Systemcited by 138
  5. 2025A Survey of Context Engineering for Large Language Modelscited by 126
  6. 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agentscited by 109
  7. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solvingcited by 94
  8. 2026Agentic Memory: Learning Unified Long-Term and Short-Term Memory Management for Large Language Model Agentscited by 78
  9. 2025MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Modelscited by 73
  10. 2025MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systemscited by 61
  11. 2026SkillOS: Learning Skill Curation for Self-Evolving Agentscited by 49
  12. 2026Code as Agent Harnesscited by 47
38 more
  1. 2025Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflectscited by 44
  2. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 44
  3. 2025StoryMem: Multi-shot Long Video Storytelling with Memorycited by 40
  4. 2026From Recall to Forgetting: Benchmarking Long-Term Memory for Personalized Agentscited by 36
  5. 2025From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agentscited by 29
  6. 2025SGMem: Sentence Graph Memory for Long-Term Conversational Agentscited by 29
  7. 2026A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecyclecited by 27
  8. 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skillscited by 22
  9. 2025MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversationscited by 21
  10. 2026From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanismscited by 21
  11. 2025StoryBench: A Dynamic Benchmark for Evaluating Long-Term Memory with Multi Turnscited by 20
  12. 2026Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agentscited by 19
  13. 2026Self-Improvements in Modern Agentic Systems: A Surveycited by 19
  14. 2025Pre-Storage Reasoning for Episodic Memory: Shifting Inference Burden to Memory for Personalized Dialoguecited by 18
  15. 2026HiMem: Hierarchical Long-Term Memory for LLM Long-Horizon Agentscited by 18
  16. 2026Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoningcited by 17
  17. 2026LatentMem: Customizing Latent Memory for Multi-Agent Systemscited by 15
  18. 2026Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agentscited by 14
  19. 2026Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directionscited by 14
  20. 2026Sycophantic AI makes human interaction feel more effortful and less satisfying over timecited by 12
  21. 2025Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physicscited by 11
  22. 2026AdaMem: Adaptive User-Centric Memory for Long-Horizon Dialogue Agentscited by 11
  23. 2026Does Memory Need Graphs? A Unified Framework and Empirical Analysis for Long-Term Dialog Memorycited by 10
  24. 2026PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoningcited by 10
  25. 2025On the Failure of Latent State Persistence in Large Language Modelscited by 9
  26. 2025Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Enhanced Model Architecturescited by 9
  27. 2025MR.Rec: Synergizing Memory and Reasoning for Personalized Recommendation Assistant with LLMscited by 9
  28. 2026FOREVER: Forgetting Curve-Inspired Memory Replay for Language Model Continual Learningcited by 8
  29. 2026Position: Modular Memory is the Key to Continual Learning Agentscited by 8
  30. 2026Chronos: Temporal-Aware Conversational Agents with Structured Event Retrieval for Long-Term Memorycited by 8
  31. 2025Adaptive Schema-aware Event Extraction with Retrieval-Augmented Generationcited by 7
  32. 2025MemOrb: A Plug-and-Play Verbal-Reinforcement Memory Layer for E-Commerce Customer Servicecited by 7
  33. 2026Retrieval-Augmented LLM Agents: Learning to Learn from Experiencecited by 7
  34. 2026Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agentscited by 7
  35. 2026User as Code: Executable Memory for Personalized Agentscited by 7
  36. 2026MemTxn: A Transaction Boundary for Source-Supported Updates and Complete-State Recovery in Agent Memorycited by 7
  37. 2026Gated Differentiable Working Memory for Long-Context Language Modelingcited by 6
  38. 2026A Mechanistic View on Video Generation as World Models: State and Dynamicscited by 6

50 most cited of 124 All 124 (JSON)