mlsanityData to 7 Oct 2026

AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agents

arXiv 2512.23343 ↗First posted 29 Dec 2025cs.CL cs.AI cs.CVcited by 12

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

Abstract (arXiv)

Memory serves as the pivotal nexus bridging past and future, providing both humans and AI systems with invaluable concepts and experience to navigate complex tasks. Recent research on autonomous agents has increasingly focused on designing efficient memory workflows by drawing on cognitive neuroscience. However, constrained by interdisciplinary barriers, existing works struggle to assimilate the essence of human memory mechanisms. To bridge this gap, we systematically synthesizes interdisciplinary knowledge of memory, connecting insights from cognitive neuroscience with LLM-driven agents. Specifically, we first elucidate the definition and function of memory along a progressive trajectory from cognitive neuroscience through LLMs to agents. We then provide a comparative analysis of memory taxonomy, storage mechanisms, and the complete management lifecycle from both biological and artificial perspectives. Subsequently, we review the mainstream benchmarks for evaluating agent memory. Additionally, we explore memory security from dual perspectives of attack and defense. Finally, we envision future research directions, with a focus on multimodal memory systems and skill acquisition.

Key facts. Cited by 12 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 172 of its 400 references that are in the map. First posted on arXiv 29 Dec 2025.

Builds on

172 of 400 references.

Closest ancestors · 51

Same direction, newest first

  1. 2025Memory in the Age of AI Agents15 Dec
  2. 2025Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution11 Dec
  3. 2025Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory25 Nov
  4. 2025General Agentic Memory Via Deep Research23 Nov
  5. 2025A Benchmark for Procedural Memory Retrieval in Language Agents21 Nov
  6. 2025From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory11 Nov
  7. 2025LiCoMemory: Lightweight and Cognitive Agentic Memory for Efficient Long-Term Reasoning3 Nov
  8. 2025AgentFold: Long-Horizon Web Agents with Proactive Context Management28 Oct
  9. 2025Learning from Supervision with Semantic and Episodic Memory: A Reflective Approach to Agent Adaptation22 Oct
  10. 2025RGMem: Renormalization Group-inspired Memory Evolution for Language Agents18 Oct
  11. 2025AUGUSTUS: An LLM-Driven Multimodal Agent System with Contextualized User Memory17 Oct
  12. 2025Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks14 Oct
38 more
  1. 2025Scaling Long-Horizon LLM Agent via Context-Folding13 Oct
  2. 2025Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles9 Oct
  3. 2025ToolMem: Enhancing Multimodal Agents with Learnable Tool Capability Memory8 Oct
  4. 2025CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension7 Oct
  5. 2025LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation6 Oct
  6. 2025Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models6 Oct
  7. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory29 Sep
  8. 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agents29 Sep
  9. 2025SGMem: Sentence Graph Memory for Long-Term Conversational Agents25 Sep
  10. 2025ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization16 Sep
  11. 2025H2R: Hierarchical Hindsight Reflection for Multi-Task LLM Agents16 Sep
  12. 2025EgoMem: Lifelong Memory Agent for Full-duplex Omnimodal Models15 Sep
  13. 2025Text2Mem: A Unified Memory Operation Language for Memory Operating System14 Sep
  14. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning27 Aug
  15. 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMs22 Aug
  16. 2025Coarse-to-Fine Grounded Memory for LLM Agent Planning21 Aug
  17. 2025Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Information18 Aug
  18. 2025Learn to Memorize: Optimizing LLM-based Agents with Adaptive Memory Framework15 Aug
  19. 2025What Deserves Memory: Adaptive Memory Distillation for LLM Agents5 Aug
  20. 2025MemoCue: Empowering LLM-Based Agents for Human Memory Recall via Strategy-Guided Querying31 Jul
  21. 2025Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents23 Jul
  22. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving8 Jul
  23. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions7 Jul
  24. 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents18 Jun
  25. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems9 Jun
  26. 2025PersonaAgent: Bridging Memory and Action for Personalized LLM Agents6 Jun
  27. 2025Memory OS of AI Agent30 May
  28. 2025MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents26 May
  29. 2025From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents26 May
  30. 2025Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control23 May
  31. 2025CAIM: Development and Evaluation of a Cognitive AI Memory Framework for Long-Term Interaction with Intelligent Agents19 May
  32. 2025LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners17 May
  33. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory28 Apr
  34. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  35. 2025Lifelong Learning of Large Language Model based Agents: A Roadmap13 Jan
  36. 2024MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants30 Sep
  37. 2024A Survey on the Memory Mechanism of Large Language Model based Agents21 Apr
  38. 2024INMS: Memory Sharing for Large Language Model based Agents15 Apr

50 newest of 51 All 51 (JSON)

Other references · 121

  1. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  2. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  3. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  4. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,270
  5. 2023A Survey on Multimodal Large Language Modelscited by 898
  6. 2024Training Large Language Models to Reason in a Continuous Latent Spacecited by 763
  7. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 721
  8. 2025Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Freecited by 266
  9. 2025MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agentcited by 235
  10. 2024VideoAgent: A Memory-augmented Multimodal Agent for Video Understandingcited by 224
  11. 2024OS-Copilot: Towards Generalist Computer Agents with Self-Improvementcited by 203
  12. 2025SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skillscited by 174
38 more
  1. 2025Know Me, Respond to Me: Benchmarking LLMs for Dynamic User Profiling and Personalized Responses at Scalecited by 163
  2. 2025LightMem: Lightweight and Efficient Memory-Augmented Generationcited by 163
  3. 2025WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learningcited by 162
  4. 2024Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streamscited by 160
  5. 2025Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrievalcited by 157
  6. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 155
  7. 2025Dynamic Cheatsheet: Test-Time Learning with Adaptive Memorycited by 146
  8. 2024AutoDefense: Multi-Agent LLM Defense against Jailbreak Attackscited by 135
  9. 2023Walking Down the Memory Maze: Beyond Context Limit through Interactive Readingcited by 129
  10. 2025EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecyclecited by 129
  11. 2025Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Taskscited by 128
  12. 2024The Emerged Security and Privacy of LLM Agent: A Survey with Case Studiescited by 127
  13. 2024Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systemscited by 126
  14. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 125
  15. 2025xbench: Tracking Agents Productivity Scaling with Profession-Aligned Real-World Evaluationscited by 118
  16. 2024Large Multimodal Agents: A Surveycited by 99
  17. 2024AIOS: LLM Agent Operating Systemcited by 94
  18. 2025A Survey on Trustworthy LLM Agents: Threats and Countermeasurescited by 93
  19. 2024The rising costs of training frontier AI modelscited by 91
  20. 2025Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memorycited by 88
  21. 2025Agent Learning via Early Experiencecited by 79
  22. 2023Advancing Transformer Architecture in Long-Context Large Language Models: A Comprehensive Surveycited by 71
  23. 2025DeepAgent: A General Reasoning Agent with Scalable Toolsetscited by 69
  24. 2025SEAgent: Self-Evolving Computer Use Agent with Autonomous Learning from Experiencecited by 68
  25. 2025WebResearcher: Unleashing unbounded reasoning capability in Long-Horizon Agentscited by 66
  26. 2023Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memorycited by 64
  27. 2025SWE-Exp: Experience-Driven Software Issue Resolutioncited by 64
  28. 2024TrojanRAG: Retrieval-Augmented Generation Can Be Backdoor Driver in Large Language Modelscited by 63
  29. 2025A-MemGuard: A Proactive Defense Framework for LLM-Based Agent Memorycited by 61
  30. 2025MemoryBench: A Benchmark for Memory and Continual Learning in LLM Systemscited by 56
  31. 2023A Comprehensive Survey on Vector Database: Storage and Retrieval Technique, Challengecited by 55
  32. 2024AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent Systemcited by 53
  33. 2025Training-Free Group Relative Policy Optimizationcited by 53
  34. 2023LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videoscited by 51
  35. 2025Scaling LLM Multi-turn RL with End-to-end Summarization-based Context Managementcited by 51
  36. 2025HaluMem: Evaluating Hallucinations in Memory Systems of Agentscited by 51
  37. 2025FLEX: Continuous Agent Evolution via Forward Learning from Experiencecited by 51
  38. 2025WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoningcited by 50

50 most cited of 121 All 121 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 12.

12 papers.

  1. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 40
  2. 2026A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecyclecited by 21
  3. 2026Beyond Static Summarization: Proactive Memory Extraction for LLM Agentscited by 20
  4. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestrationcited by 11
  5. 2026Fine-Mem: Fine-Grained Feedback Alignment for Long-Horizon Memory Managementcited by 8
  6. 2026HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agentscited by 5
  7. 2026A Systematic Investigation of Document Chunking Strategies and Embedding Sensitivitycited by 3
  8. 2026Scaling Self-Evolving Agents via Parametric Memorycited by 3
  9. 2026M3Eval: Multi-Modal Memory Evaluation through Cognitively-Grounded Video Taskscited by 1
  10. 2026SRTJ: Self-Evolving Rule-Driven Training-Free LLM Jailbreakingcited by 0
  11. 2026OpenClaw and Ollama in Agentic AI: Toward Fully Autonomous and Scalable AI Agent Systemscited by 0
  12. 2026VeriPhy: Agentic Physical Reasoning for World Model Evaluation and Refinementcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Contextual Agentic Memory is a Memo, Not True Memory
  2. 2026FSFM: A Biologically-Inspired Framework for Selective Forgetting of Agent Memory
  3. 2026Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents
  4. 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
  5. 2026BMAM: Brain-inspired Multi-Agent Memory Framework
  6. 2026BrainMem: Brain-Inspired Evolving Memory for Embodied Agent Task Planning
  7. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
  8. 2026The AI Hippocampus: How Far are We From Human Memory?