mlsanityData to 14 Oct 2026

Memp: Exploring Agent Procedural Memory

arXiv 2508.06433 ↗First posted 8 Aug 2025cs.CL cs.AI cs.LGcited by 103

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

Abstract (arXiv)

Large Language Models (LLMs) based agents excel at diverse tasks, yet they suffer from brittle procedural memory that is manually engineered or entangled in static parameters. In this work, we investigate strategies to endow agents with a learnable, updatable, and lifelong procedural memory. We propose Memp that distills past agent trajectories into both fine-grained, step-by-step instructions and higher-level, script-like abstractions, and explore the impact of different strategies for Build, Retrieval, and Update of procedural memory. Coupled with a dynamic regimen that continuously updates, corrects, and deprecates its contents, this repository evolves in lockstep with new experience. Empirical evaluation on TravelPlanner and ALFWorld shows that as the memory repository is refined, agents achieve steadily higher success rates and greater efficiency on analogous tasks. Moreover, procedural memory built from a stronger model retains its value: migrating the procedural memory to a weaker model can also yield substantial performance gains. Code is available at https://github.com/zjunlp/MemP.

Key facts. Cited by 103 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 38 of its 54 references that are in the map. First posted on arXiv 8 Aug 2025.

Builds on

38 of 54 references.

Closest ancestors · 7

Same direction, newest first

  1. 2025Agent KB: Leveraging Cross-Domain Experience for Agentic Problem Solving8 Jul
  2. 2025MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents18 Jun
  3. 2025Contextual Experience Replay for Self-Improvement of Language Agents7 Jun
  4. 2025A-MEM: Agentic Memory for LLM Agents17 Feb
  5. 2024HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model18 Aug
  6. 2024A Survey on the Memory Mechanism of Large Language Model based Agents21 Apr
  7. 2024"My agent understands me better": Integrating Dynamic Human-like Memory Recall and Consolidation in LLM-Based Agents31 Mar

Other references · 31

  1. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,242
  2. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,439
  3. 2024τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domainscited by 1,402
  4. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  5. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,205
  6. 2025UI-TARS: Pioneering Automated GUI Interaction with Native Agentscited by 610
  7. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 392
  8. 2023A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesiscited by 353
  9. 2023Auto-GPT for Online Decision Making: Benchmarks and Additional Opinionscited by 255
  10. 2022Reasoning with Language Model Prompting: A Surveycited by 252
  11. 2025MemAgent: Reshaping Long-Context LLM with Multi-Conv RL-based Memory Agentcited by 246
  12. 2025GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agentscited by 244
19 more
  1. 2023Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Controlcited by 187
  2. 2025WebWalker: Benchmarking LLMs in Web Traversalcited by 175
  3. 2025MemOS: A Memory OS for AI Systemcited by 138
  4. 2025Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Taskscited by 131
  5. 2025Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systemscited by 126
  6. 2023Agents: An Open-source Framework for Autonomous Language Agentscited by 116
  7. 2024Symbolic Learning Enables Self-Evolving Agentscited by 106
  8. 2025Learn-by-interact: A Data-Centric Framework for Self-Adaptive Agents in Realistic Environmentscited by 95
  9. 2025ARPO:End-to-End Policy Optimization for GUI Agents with Experience Replaycited by 77
  10. 2025ACEBench: Who Wins the Match Point in Tool Usage?cited by 71
  11. 2023Embodied Multi-Modal Agent trained by an LLM from a Parallel TextWorldcited by 65
  12. 2024AutoManual: Constructing Instruction Manuals by LLM Agents via Interactive Environmental Learningcited by 61
  13. 2024Autonomous LLM-driven research from data to human-verifiable research paperscited by 53
  14. 2023Prompt, Plan, Perform: LLM-based Humanoid Control via Quantized Imitation Learningcited by 31
  15. 2025ML-Agent: Reinforcing LLM Agents for Autonomous Machine Learning Engineeringcited by 26
  16. 2025Get Experience from Practice: LLM Agents with Record & Replaycited by 23
  17. 2025AutoMind: Adaptive Knowledgeable Agent for Automated Data Sciencecited by 20
  18. 2025Minerva: A Programmable Memory Test Benchmark for Language Modelscited by 9
  19. 2025SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinementcited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 95.

103 papers.

Sort:

By area:

  1. 2025Memory in the Age of AI Agentscited by 303
  2. 2025ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memorycited by 284
  3. 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learningcited by 278
  4. 2026SkillOpt: Executive Strategy for Self-Evolving Agent Skillscited by 148
  5. 2026MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memorycited by 129
  6. 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agentscited by 109
  7. 2026SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalizationcited by 94
  8. 2026SkillClaw: Let Skills Evolve Collectively with Agentic Evolvercited by 81
  9. 2026SkillX: Automatically Constructing Skill Knowledge Bases for Agentscited by 76
  10. 2026SkillOS: Learning Skill Curation for Self-Evolving Agentscited by 49
  11. 2026Skill-Pro: Learning Reusable Skills from Experience via Non-Parametric PPO for LLM Agentscited by 47
  12. 2026A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agentscited by 44
38 more
  1. 2026MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wildcited by 37
  2. 2026Skill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learningcited by 35
  3. 2026PlugMem: A Task-Agnostic Plugin Memory Module for LLM Agentscited by 32
  4. 2025Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Taskscited by 22
  5. 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skillscited by 22
  6. 2026From Raw Experience to Skill Consumption: A Systematic Study of Model-Generated Agent Skillscited by 22
  7. 2026Learning to Continually Learn via Meta-learning Agentic Memory Designscited by 18
  8. 2026StructMem: Structured Memory for Long-Horizon Behavior in LLMscited by 18
  9. 2026SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolutioncited by 18
  10. 2026EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agentscited by 16
  11. 2026SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphscited by 15
  12. 2026MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agentscited by 11
  13. 2026Auto-Dreamer: Learning Offline Memory Consolidation for Language Agentscited by 10
  14. 2026From Procedural Skills to Strategy Genes: Towards Experience-Driven Test-Time Evolutioncited by 9
  15. 2026Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement Learningcited by 9
  16. 2026SkillMaster: Toward Autonomous Skill Mastery in LLM Agentscited by 8
  17. 2026Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Applicationcited by 8
  18. 2026LMEB: Long-horizon Memory Embedding Benchmarkcited by 7
  19. 2026Memory Intelligence Agentcited by 7
  20. 2026Co-Evolving Skill Generation and Policy Optimizationcited by 7
  21. 2026Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix Itcited by 7
  22. 2026Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agentscited by 7
  23. 2025PowerChain: A Verifiable Agentic AI System for Automating Distribution Grid Analysescited by 6
  24. 2025Nested Browser-Use Learning for Agentic Information Seekingcited by 6
  25. 2026SkillLens: Adaptive Multi-Granularity Skill Reuse for Cost-Efficient LLM Agentscited by 6
  26. 2026Harness Continual Learning: Continual Adaptation Beyond Model Parameterscited by 6
  27. 2026Always-OnAgents:A Survey of Persistent Memory, State, and Governance in LLMAgentscited by 5
  28. 2026TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflowscited by 5
  29. 2026ElasticMem: Latent Memory as a Learnable Resource for LLM Agentscited by 4
  30. 2026Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memorycited by 4
  31. 2026MemHarness: Memory Is Reconstructed, Not Replayedcited by 4
  32. 2025A Scenario-Driven Cognitive Approach to Next-Generation AI Memorycited by 3
  33. 2026Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesiscited by 3
  34. 2026FileGram: Grounding Agent Personalization in File-System Behavioral Tracescited by 3
  35. 2026Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agentscited by 3
  36. 2026Speculate with Memory: Lossless Acceleration for LLM Agentscited by 3
  37. 2026Learning to Share: Selective Memory for Efficient Parallel Agentic Systemscited by 2
  38. 2026Unsupervised Skill Discovery for Agentic Data Analysiscited by 2

50 most cited of 103 All 103 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026AdMem: Advanced Memory for Task-solving Agents
  2. 2025Remember Me, Refine Me: A Dynamic Procedural Memory Framework for Experience-Driven Agent Evolution
  3. 2026MemGym: a Long-Horizon Memory Environment for LLM Agents
  4. 2026Are We Ready For An Agent-Native Memory System?
  5. 2026EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective
  6. 2026Memory for Autonomous LLM Agents:Mechanisms, Evaluation, and Emerging Frontiers
  7. 2026MemPro: Agentic Memory Systems as Evolvable Programs
  8. 2026MemReader: From Passive to Active Extraction for Long-Term Agent Memory