mlsanityData to 7 Oct 2026

Memory in the Age of AI Agents

arXiv 2512.13564 ↗First posted 15 Dec 2025cs.CL cs.AIcited by 285

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

Abstract (arXiv)

Memory has emerged, and will continue to remain, a core capability of foundation model-based agents. As research on agent memory rapidly expands and attracts unprecedented attention, the field has also become increasingly fragmented. Existing works that fall under the umbrella of agent memory often differ substantially in their motivations, implementations, and evaluation protocols, while the proliferation of loosely defined memory terminologies has further obscured conceptual clarity. Traditional taxonomies such as long/short-term memory have proven insufficient to capture the diversity of contemporary agent memory systems. This work aims to provide an up-to-date landscape of current agent memory research. We begin by clearly delineating the scope of agent memory and distinguishing it from related concepts such as LLM memory, retrieval augmented generation (RAG), and context engineering. We then examine agent memory through the unified lenses of forms, functions, and dynamics. From the perspective of forms, we identify three dominant realizations of agent memory, namely token-level, parametric, and latent memory. From the perspective of functions, we propose a finer-grained taxonomy that distinguishes factual, experiential, and working memory. From the perspective of dynamics, we analyze how memory is formed, evolved, and retrieved over time. To support practical development, we compile a comprehensive summary of memory benchmarks and open-source frameworks. Beyond consolidation, we articulate a forward-looking perspective on emerging research frontiers, including memory automation, reinforcement learning integration, multimodal memory, multi-agent memory, and trustworthiness issues. We hope this survey serves not only as a reference for existing work, but also as a conceptual foundation for rethinking memory as a first-class primitive in the design of future agentic intelligence.

Key facts. Cited by 285 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 266 of its 490 references that are in the map. First posted on arXiv 15 Dec 2025.

Builds on

266 of 490 references.

Closest ancestors · 53

Same direction, newest first

  1. 2025Hindsight is 20/20: Building Agent Memory that Retains, Recalls, and Reflects14 Dec
  2. 2025Memoria: A Scalable Agentic Memory Framework for Personalized Conversational AI14 Dec
  3. 2025Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution11 Dec
  4. 2025Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory25 Nov
  5. 2025General Agentic Memory Via Deep Research23 Nov
  6. 2025A Simple Yet Strong Baseline for Long-Term Conversational Memory of LLM Agents21 Nov
  7. 2025O-Mem: Omni Memory System for Personalized, Long Horizon, Self-Evolving Agents17 Nov
  8. 2025From Experience to Strategy: Empowering LLM Agents with Trainable Graph Memory11 Nov
  9. 2025Dynamic Affective Memory Management for Personalized LLM Agents31 Oct
  10. 2025AgentFold: Long-Horizon Web Agents with Proactive Context Management28 Oct
  11. 2025Learning from Supervision with Semantic and Episodic Memory: A Reflective Approach to Agent Adaptation22 Oct
  12. 2025RGMem: Renormalization Group-inspired Memory Evolution for Language Agents18 Oct
38 more
  1. 2025Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks14 Oct
  2. 2025Scaling Long-Horizon LLM Agent via Context-Folding13 Oct
  3. 2025Enabling Personalized Long-term Interactions in LLM-based Agents through Persistent Memory and User Profiles9 Oct
  4. 2025ToolMem: Enhancing Multimodal Agents with Learnable Tool Capability Memory8 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. 2025Look Back to Reason Forward: Revisitable Memory for Long-Context LLM Agents27 Sep
  9. 2025ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization16 Sep
  10. 2025H2R: Hierarchical Hindsight Reflection for Multi-Task LLM Agents16 Sep
  11. 2025Memory-R1: Enhancing Large Language Model Agents to Manage and Utilize Memories via Reinforcement Learning27 Aug
  12. 2025Memento: Fine-tuning LLM Agents without Fine-tuning LLMs22 Aug
  13. 2025Explicit v.s. Implicit Memory: Exploring Multi-hop Complex Reasoning Over Personalized Information18 Aug
  14. 2025Semantic Anchoring in Agentic Memory: Leveraging Linguistic Structures for Persistent Conversational Context18 Aug
  15. 2025Learn to Memorize: Optimizing LLM-based Agents with Adaptive Memory Framework15 Aug
  16. 2025Intrinsic Memory Agents: Heterogeneous Multi-Agent LLM Systems through Structured Contextual Memory12 Aug
  17. 2025Memp: Exploring Agent Procedural Memory8 Aug
  18. 2025What Deserves Memory: Adaptive Memory Distillation for LLM Agents5 Aug
  19. 2025MIRIX: Multi-Agent Memory System for LLM-Based Agents10 Jul
  20. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving8 Jul
  21. 2025Evaluating Memory in LLM Agents via Incremental Multi-Turn Interactions7 Jul
  22. 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents18 Jun
  23. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems9 Jun
  24. 2025Memory OS of AI Agent30 May
  25. 2025MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents26 May
  26. 2025Collaborative Memory: Multi-User Memory Sharing in LLM Agents with Dynamic Access Control23 May
  27. 2025Embodied Agents Meet Personalization: Investigating Challenges and Solutions Through the Lens of Memory Utilization22 May
  28. 2025LifelongAgentBench: Evaluating LLM Agents as Lifelong Learners17 May
  29. 2025MemEngine: A Unified and Modular Library for Developing Advanced Memory of LLM-based Agents4 May
  30. 2025Rethinking Memory in LLM based Agents: Representations, Operations, and Emerging Topics1 May
  31. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory28 Apr
  32. 2025MemInsight: Autonomous Memory Augmentation for LLM Agents27 Mar
  33. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  34. 2025Zep: A Temporal Knowledge Graph Architecture for Agent Memory20 Jan
  35. 2024Memory-Augmented Agent Training for Business Document Understanding17 Dec
  36. 2024Crafting Personalized Agents through Retrieval-Augmented Generation on Editable Memory Graphs28 Sep
  37. 2024AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents5 Jul
  38. 2024Towards Lifelong Dialogue Agents via Timeline-based Memory Management16 Jun

50 newest of 53 All 53 (JSON)

Other references · 213

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2024The Llama 3 Herd of Modelscited by 14,192
  3. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,146
  5. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  6. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  7. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  8. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  9. 2020DeBERTa: Decoding-enhanced BERT with Disentangled Attentioncited by 2,157
  10. 2023WebArena: A Realistic Web Environment for Building Autonomous Agentscited by 1,908
  11. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  12. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
38 more
  1. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  2. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  3. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,270
  4. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  5. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  6. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 893
  7. 2025Large Language Diffusion Modelscited by 872
  8. 2023RWKV: Reinventing RNNs for the Transformer Eracited by 814
  9. 2025BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agentscited by 616
  10. 2024Large Language Models: A Surveycited by 506
  11. 2023Zephyr: Direct Distillation of LM Alignmentcited by 498
  12. 2022XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Modelcited by 436
  13. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Modelscited by 423
  14. 2024PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funnelingcited by 420
  15. 2024Jamba: A Hybrid Transformer-Mamba Language Modelcited by 390
  16. 2023Orca: Progressive Learning from Complex Explanation Traces of GPT-4cited by 369
  17. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learningcited by 322
  18. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
  19. 2025WebThinker: Empowering Large Reasoning Models with Deep Research Capabilitycited by 320
  20. 2024Titans: Learning to Memorize at Test Timecited by 303
  21. 2022ScienceWorld: Is your Agent Smarter than a 5th Grader?cited by 298
  22. 2025Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agentscited by 294
  23. 2025Reinforcement Learning for Reasoning in Large Language Models with One Training Examplecited by 288
  24. 2021Recursively Summarizing Books with Human Feedbackcited by 287
  25. 2023FireAct: Toward Language Agent Fine-tuningcited by 247
  26. 2025Agentic Retrieval-Augmented Generation: A Survey on Agentic RAGcited by 242
  27. 2018BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learningcited by 238
  28. 2025MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agentcited by 235
  29. 2023S3: Social-network Simulation System with Large Language Model-Empowered Agentscited by 228
  30. 2024RepairAgent: An Autonomous, LLM-Based Agent for Program Repaircited by 225
  31. 2024AlphaEdit: Null-Space Constrained Knowledge Editing for Language Modelscited by 224
  32. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 223
  33. 2025WebSailor: Navigating Super-human Reasoning for Web Agentcited by 218
  34. 2025Rolling Forcing: Autoregressive Long Video Diffusion in Real Timecited by 209
  35. 2023Transformer-Patcher: One Mistake worth One Neuroncited by 196
  36. 2025The Landscape of Agentic Reinforcement Learning for LLMs: A Surveycited by 195
  37. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challengescited by 194
  38. 2025MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulationcited by 183

50 most cited of 213 All 213 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 5; 2026: 280.

285 papers.

Sort:

By area:

  1. 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learningcited by 252
  2. 2026SimpleMem: Efficient Lifelong Memory for LLM Agentscited by 140
  3. 2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agentscited by 129
  4. 2025MemEvolve: Meta-Evolution of Agent Memory Systemscited by 81
  5. 2026MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Taskscited by 72
  6. 2026XSkill: Continual Learning from Experience and Skills in Multimodal Agentscited by 71
  7. 2026SkillX: Automatically Constructing Skill Knowledge Bases for Agentscited by 69
  8. 2026MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agentscited by 49
  9. 2026Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agentscited by 49
  10. 2026SkillOS: Learning Skill Curation for Self-Evolving Agentscited by 45
  11. 2026Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agentscited by 44
  12. 2026Meta Context Engineering via Agentic Skill Evolutioncited by 42
38 more
  1. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 40
  2. 2026HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understandingcited by 36
  3. 2026Dive into Claude Code: The Design Space of Today's and Future AI Agent Systemscited by 33
  4. 2026Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineeringcited by 26
  5. 2026InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discoverycited by 24
  6. 2026ExpSeek: Self-Triggered Experience Seeking for Web Agentscited by 23
  7. 2026From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agentscited by 23
  8. 2026AgentOCR: Reimagining Agent History via Optical Self-Compressioncited by 22
  9. 2026A Survey on Long-Term Memory Security in LLM Agents: Attacks, Defenses, and Governance Across the Memory Lifecyclecited by 21
  10. 2026RealMem: Benchmarking LLMs in Real-World Memory-Driven Interactioncited by 20
  11. 2026Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitationscited by 20
  12. 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skillscited by 19
  13. 2026GAM: Hierarchical Graph-based Agentic Memory for LLM Agentscited by 19
  14. 2026Building Effective AI Coding Agents for the Terminal: Scaffolding, Harness, Context Engineering, and Lessons Learnedcited by 18
  15. 2026Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoningcited by 17
  16. 2026Learning to Continually Learn via Meta-learning Agentic Memory Designscited by 16
  17. 2026Self-Play Only Evolves When Self-Synthetic Pipeline Ensures Learnable Information Gaincited by 16
  18. 2026Governing Evolving Memory in LLM Agents: Risks, Mechanisms, and the Stability and Safety Governed Memory (SSGM) Frameworkcited by 16
  19. 2026Experience Compression Spectrum: Unifying Memory, Skills, and Rules in LLM Agentscited by 16
  20. 2026MemOCR: Layout-Aware Visual Memory for Efficient Long-Horizon Reasoningcited by 15
  21. 2026Beyond RAG for Agent Memory: Retrieval by Decoupling and Aggregationcited by 15
  22. 2026Beyond Dialogue Time: Temporal Semantic Memory for Personalized LLM Agentscited by 14
  23. 2026Mem-T: Densifying Rewards for Long-Horizon Memory Agentscited by 14
  24. 2026MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agentscited by 14
  25. 2026PERMA: Benchmarking Personalized Memory Agents via Event-Driven Preference and Realistic Task Environmentscited by 13
  26. 2026ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agentscited by 13
  27. 2025AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agentscited by 12
  28. 2026MemoBrain: Executive Memory as an Agentic Brain for Reasoningcited by 12
  29. 2026LatentMem: Customizing Latent Memory for Multi-Agent Systemscited by 12
  30. 2026Learning Query-Aware Budget-Tier Routing for Runtime Agent Memorycited by 12
  31. 2026Evaluating Memory Structure in LLM Agentscited by 12
  32. 2026Hybrid Self-evolving Structured Memory for GUI Agentscited by 12
  33. 2026Memori: A Persistent Memory Layer for Efficient, Context-Aware LLM Agentscited by 12
  34. 2026Experiential Reflective Learning for Self-Improving LLM Agentscited by 12
  35. 2026Memory in the LLM Era: Modular Architectures and Strategies in a Unified Frameworkcited by 12
  36. 2026Trojan Hippo: Weaponizing Agent Memory for Data Exfiltrationcited by 12
  37. 2026Learning Agent-Compatible Context Management for Long-Horizon Taskscited by 12
  38. 2026Toward Efficient Agents: Memory, Tool learning, and Planningcited by 11

50 most cited of 285 All 285 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
  2. 2026EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective
  3. 2026Graph-based Agent Memory: Taxonomy, Techniques, and Applications
  4. 2026AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications
  5. 2026Agent Memory: Characterization and System Implications of Stateful Long-Horizon Workloads
  6. 2026From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms
  7. 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agents
  8. 2026Measure Before You Manage: Evaluating Agent Working Memory in Coding Agents