mlsanityData to 14 Oct 2026

Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution

arXiv 2512.10696 ↗First posted 11 Dec 2025cs.AI cs.CLcited by 73

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

Abstract (arXiv)

Procedural memory enables large language model (LLM) agents to internalize "how-to" knowledge, theoretically reducing redundant trial-and-error. However, existing frameworks predominantly suffer from a "passive accumulation" paradigm, treating memory as a static append-only archive. To bridge the gap between static storage and dynamic reasoning, we propose ReMe (textitRemember Me, Refine Me), a comprehensive framework for experience-driven agent evolution. ReMe innovates across the memory lifecycle via three mechanisms: 1) textitmulti-faceted distillation, which extracts fine-grained experiences by recognizing success patterns, analyzing failure triggers and generating comparative insights; 2) textitcontext-adaptive reuse, which tailors historical insights to new contexts via scenario-aware indexing; and 3) textitutility-based refinement, which autonomously adds valid memories and prunes outdated ones to maintain a compact, high-quality experience pool. Extensive experiments on BFCL-V3 and AppWorld demonstrate that ReMe establishes a new state-of-the-art in agent memory system. Crucially, we observe a significant memory-scaling effect: Qwen3-8B equipped with ReMe outperforms larger, memoryless Qwen3-14B, suggesting that self-evolving memory provides a computation-efficient pathway for lifelong learning. We release our code and the textttreme.library dataset to facilitate further research.

Key facts. Cited by 73 papers in the map (data through 14 Oct 2026). Placed in Agent memory systems, one of 16 directions in LLM agents and tool use. Builds on 19 of its 33 references that are in the map. First posted on arXiv 11 Dec 2025.

Builds on

19 of 33 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025MIRIX: Multi-Agent Memory System for LLM-Based Agents10 Jul
  2. 2025Contextual Experience Replay for Self-Improvement of Language Agents7 Jun
  3. 2025How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior21 May
  4. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  5. 2024A Survey on the Memory Mechanism of Large Language Model based Agents21 Apr

Other references · 14

  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,626
  2. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
  3. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
  4. 2024AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agentscited by 401
  5. 2024Large Language Models for Education: A Survey and Outlookcited by 188
  6. 2023Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Controlcited by 187
  7. 2025A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systemscited by 183
  8. 2025A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencecited by 170
  9. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospectscited by 132
  10. 2023Conversational Health Agents: A Personalized LLM-Powered Agent Frameworkcited by 92
  11. 2024Agent Planning with World Knowledge Modelcited by 70
  12. 2025SWE-Exp: Experience-Driven Software Issue Resolutioncited by 65
2 more
  1. 2024Large Language Model Agent in Financial Trading: A Surveycited by 60
  2. 2025MARK: Memory Augmented Refinement of Knowledgecited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 70.

73 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 303
  2. 2026SkillX: Automatically Constructing Skill Knowledge Bases for Agentscited by 76
  3. 2026XSkill: Continual Learning from Experience and Skills in Multimodal Agentscited by 75
  4. 2026ExpSeek: Self-Triggered Experience Seeking for Web Agentscited by 23
  5. 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skillscited by 22
  6. 2026Anatomy of Agentic Memory: Taxonomy and Empirical Analysis of Evaluation and System Limitationscited by 21
  7. 2026From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanismscited by 21
  8. 2026SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolutioncited by 18
  9. 2026Position: Agentic Evolution is the Path to Evolving LLMscited by 16
  10. 2026EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agentscited by 16
  11. 2026ReSkill: Reconciling Skill Creation with Policy Optimization in Agentic RLcited by 14
  12. 2025AI Meets Brain: Memory Systems from Cognitive Neuroscience to Autonomous Agentscited by 12
38 more
  1. 2026Learning How to Remember: A Meta-Cognitive Management Method for Structured and Transferable Agent Memorycited by 10
  2. 2026TAME: A Trustworthy Test-Time Evolution of Agent Memory with Systematic Benchmarkingcited by 10
  3. 2026When Continual Learning Moves to Memory: A Study of Experience Reuse in LLM Agentscited by 10
  4. 2026Position: Beyond Model-Centric Prediction -- Agentic Time Series Forecastingcited by 9
  5. 2026MemCast: Memory-Driven Time Series Forecasting with Experience-Conditioned Reasoningcited by 9
  6. 2026Evolving-RL: End-to-End Optimization of Experience-Driven Self-Evolving Capability within Agentscited by 9
  7. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  8. 2026LMEB: Long-horizon Memory Embedding Benchmarkcited by 7
  9. 2026Memory Intelligence Agentcited by 7
  10. 2026Co-Evolving Skill Generation and Policy Optimizationcited by 7
  11. 2026Gated Differentiable Working Memory for Long-Context Language Modelingcited by 6
  12. 2026GSEM: Graph-based Self-Evolving Memory for Experience Augmented Clinical Reasoningcited by 6
  13. 2026Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improvecited by 6
  14. 2026MemTrace: Tracing and Attributing Errors in Large Language Model Memory Systemscited by 6
  15. 2026RaMem: Contextual Reinstatement for Long-term Agentic Memorycited by 6
  16. 2026Aligning Agentic World Models via Knowledgeable Experience Learningcited by 5
  17. 2026MemQ: Integrating Q-Learning into Self-Evolving Memory Agents over Provenance DAGscited by 5
  18. 2026Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agentscited by 5
  19. 2026Context as an Environment: Programmatic Context Management for Long-Horizon Agentscited by 4
  20. 2026Scaling Small Agents Through Strategy Auctionscited by 3
  21. 2026MemPro: Agentic Memory Systems as Evolvable Programscited by 3
  22. 2026PhotoCraft: Agentic Reasoning with Hierarchical Self-Evolving Memory for Deep Image Searchcited by 3
  23. 2026FinEvolveBench: A Benchmark for Self-Evolving Agents on Low-Repetition Tasks with Implicit Rewardscited by 3
  24. 2026Pushing the Limits of LLM Tool Calling via Experiential Knowledge Integration and Activationcited by 3
  25. 2026Self-evolving Embodied AIcited by 2
  26. 2026Towards Effective Experiential Learning: Dual Guidance for Utilization and Internalizationcited by 2
  27. 2026MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcarecited by 2
  28. 2026MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoningcited by 2
  29. 2026ConMem: Structured Memory-Guided Adaptation in Training-Free Multi-Agent Systemscited by 2
  30. 2026Metis: Bridging Text and Code Memory for Self-Evolving Agentscited by 2
  31. 2026Can Large Language Models Forecast What Researchers Study Next?cited by 2
  32. 2026WorkflowGen:an adaptive workflow generation mechanism driven by trajectory experiencecited by 1
  33. 2026EXG: Self-Evolving Agents with Experience Graphscited by 1
  34. 2026Rethinking Memory as Continuously Evolving Connectivitycited by 1
  35. 2026AgentSpec: Understanding Embodied Agent Scaffolds Through Controlled Compositioncited by 1
  36. 2026EvoHarness-RL: Learning Self-Evolving Runtime Harness for Long-Horizon LLM Agentscited by 1
  37. 2026Agents in the Large: Perception-Centered Architecture for Persistent Agentscited by 1
  38. 2026Learning What to Practice: Diagnosis-Guided Self-Evolution for Language Modelscited by 1

50 most cited of 73 All 73 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Memp: Exploring Agent Procedural Memory
  2. 2025MemEvolve: Meta-Evolution of Agent Memory Systems
  3. 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agents
  4. 2026Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents
  5. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents
  6. 2026AdMem: Advanced Memory for Task-solving Agents
  7. 2026SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent
  8. 2026MemHarness: Memory Is Reconstructed, Not Replayed