让智能体具备可学习、可更新的长期程序记忆，提升任务成功率。
Memp: Exploring Agent Procedural Memory
- 将历史行为提炼为细粒度指令与高层脚本，构建可进化记忆库。
- 在TravelPlanner和ALFWorld上，记忆优化后成功率稳步提升。
- 强模型生成的记忆可迁移到弱模型，仍能显著提效，适合长期任务代理。
基于大语言模型的智能体虽能完成多样任务，但其程序记忆脆弱，依赖人工设计或静态参数。本文提出Memp，旨在赋予智能体可学习、可更新、终身演化的程序记忆。该方法将过往智能体轨迹提炼为细粒度步骤指令与高层脚本抽象，并探索记忆的构建、检索与更新策略。结合动态机制持续更新、修正与淘汰记忆内容，记忆库随新经验同步演化。在TravelPlanner和ALFWorld上的实证表明，随着记忆库的完善，智能体在相似任务上的成功率与效率持续提升。此外，由强模型生成的记忆具有迁移价值：迁移到弱模型仍能带来显著性能增益。代码已开源：https://github.com/zjunlp/MemP。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。