mlsanityData to 7 Oct 2026

Memory OS of AI Agent

arXiv 2506.06326 ↗First posted 30 May 2025cs.AIcited by 140

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

Abstract (arXiv)

Large Language Models (LLMs) face a crucial challenge from fixed context windows and inadequate memory management, leading to a severe shortage of long-term memory capabilities and limited personalization in the interactive experience with AI agents. To overcome this challenge, we innovatively propose a Memory Operating System, i.e., MemoryOS, to achieve comprehensive and efficient memory management for AI agents. Inspired by the memory management principles in operating systems, MemoryOS designs a hierarchical storage architecture and consists of four key modules: Memory Storage, Updating, Retrieval, and Generation. Specifically, the architecture comprises three levels of storage units: short-term memory, mid-term memory, and long-term personal memory. Key operations within MemoryOS include dynamic updates between storage units: short-term to mid-term updates follow a dialogue-chain-based FIFO principle, while mid-term to long-term updates use a segmented page organization strategy. Our pioneering MemoryOS enables hierarchical memory integration and dynamic updating. Extensive experiments on the LoCoMo benchmark show an average improvement of 49.11% on F1 and 46.18% on BLEU-1 over the baselines on GPT-4o-mini, showing contextual coherence and personalized memory retention in long conversations. The implementation code is open-sourced at https://github.com/BAI-LAB/MemoryOS.

Key facts. Cited by 140 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 11 of its 21 references that are in the map. First posted on arXiv 30 May 2025.

Builds on

11 of 21 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  2. 2024Hello Again! LLM-powered Personalized Agent for Long-term Dialogue9 Jun
  3. 2024A Survey on the Memory Mechanism of Large Language Model based Agents21 Apr
  4. 2024Evaluating Very Long-Term Conversational Memory of LLM Agents27 Feb

Other references · 7

  1. 2025From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMscited by 119
  2. 2023SCM: Enhancing Large Language Model with Self-Controlled Memory Frameworkcited by 98
  3. 2023LLM-based Medical Assistant Personalization with Short- and Long-Term Memory Coordinationcited by 46
  4. 2024Personalized LLM Response Generation with Parameterized Memory Injectioncited by 33
  5. 2025From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignmentcited by 28
  6. 2024Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrievalcited by 26
  7. 2024Generative Dense Retrieval: Memory Can Be a Burdencited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 18; 2026: 122.

140 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 285
  2. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactionscited by 236
  3. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 163
  4. 2025MIRIX: Multi-Agent Memory System for LLM-Based Agentscited by 160
  5. 2026SimpleMem: Efficient Lifelong Memory for LLM Agentscited by 140
  6. 2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agentscited by 129
  7. 2025A Survey of Context Engineering for Large Language Modelscited by 120
  8. 2025Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memorycited by 88
  9. 2025MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systemscited by 56
  10. 2026EverMemOS: A Self-Organizing Memory Operating System for Structured Long-Horizon Reasoningcited by 52
  11. 2025HaluMem: Evaluating Hallucinations in Memory Systems of Agentscited by 51
  12. 2025General Agentic Memory Via Deep Researchcited by 42
38 more
  1. 2025O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agentscited by 30
  2. 2025SGMem: Sentence Graph Memory for Long-Term Conversational Agentscited by 29
  3. 2026TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agentscited by 26
  4. 2026From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agentscited by 23
  5. 2025AgenticData: An Agentic Data Analytics System for Heterogeneous Datacited by 22
  6. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applicationscited by 22
  7. 2026Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agentscited by 16
  8. 2025WebCoach: Self-Evolving Web Agents with Cross-Session Memory Guidancecited by 15
  9. 2026Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregationcited by 15
  10. 2026Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agentscited by 14
  11. 2026EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspectivecited by 14
  12. 2026FadeMem: Biologically-Inspired Forgetting for Efficient Agent Memorycited by 13
  13. 2025AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agentscited by 12
  14. 2026MemoBrain: Executive Memory as an Agentic Brain for Reasoningcited by 12
  15. 2026Learning Query-Aware Budget-Tier Routing for Runtime Agent Memorycited by 12
  16. 2026Evaluating Memory Structure in LLM Agentscited by 12
  17. 2026According to Me: Long-Term Personalized Referential Memory QAcited by 12
  18. 2026Memex(RL): Scaling Long-Horizon LLM Agents via Indexed Experience Memorycited by 11
  19. 2026E-mem: Multi-agent based Episodic Context Reconstruction for LLM Agent Memorycited by 10
  20. 2026Choosing How to Remember: Adaptive Memory Structures for LLM Agentscited by 10
  21. 2026PersonaVLM: Long-Term Personalized Multimodal LLMscited by 10
  22. 2025Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Enhanced Model Architecturescited by 9
  23. 2026Belief Memory: Agent Memory Under Partial Observabilitycited by 9
  24. 2026Memory is Reconstructed, Not Retrieved: Graph Memory for LLM Agentscited by 9
  25. 2026MemSyco-Bench: Benchmarking Sycophancy in Agent Memorycited by 9
  26. 2026All-Mem: Agentic Lifelong Memory via Dynamic Topology Evolutioncited by 8
  27. 2026Quantifying Trust: Financial Risk Management for Trustworthy AI Agentscited by 8
  28. 2026ActMem: Bridging the Gap Between Memory Retrieval and Reasoning in LLM Agentscited by 6
  29. 2026AlpsBench: An LLM Personalization Benchmark for Real-Dialogue Memorization and Preference Alignmentcited by 6
  30. 2026PM-Bench: Evaluating Prospective Memory in LLM Agentscited by 6
  31. 2026RaMem: Contextual Reinstatement for Long-term Agentic Memorycited by 5
  32. 2026TRUSTMEM: Learning Trustworthy Memory Consolidation for LLM Agents with Long-Term Memorycited by 5
  33. 2025EgoMem: Lifelong Memory Agent for Full-duplex Omnimodal Modelscited by 4
  34. 2026LLMs Can't Play Hangman: On the Necessity of a Private Working Memory for Language Agentscited by 4
  35. 2026ClawVM: Harness-Managed Virtual Memory for Stateful Tool-Using LLM Agentscited by 4
  36. 2026Agentic Recommender System with Hierarchical Belief-State Memorycited by 4
  37. 2026H-Mem: A Novel Memory Mechanism for Evolving and Retrieving Agent Memory via a Hybrid Structurecited by 4
  38. 2026ElasticMem: Latent Memory as a Learnable Resource for LLM Agentscited by 4

50 most cited of 140 All 140 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025MemOS: A Memory OS for AI System
  2. 2025MemOS: An Operating System for Memory-Augmented Generation (MAG) in Large Language Models
  3. 2024The Compressor-Retriever Architecture for Language Model OS
  4. 2026Are We Ready For An Agent-Native Memory System?
  5. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics
  6. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
  7. 2025Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents
  8. 2024On the Structural Memory of LLM Agents