paper-with-me

Papers

Memp: Exploring Agent Procedural Memory

2025-08-08 · Runnan Fang, Yuan Liang, Xiaobin Wang, Jialong Wu, Shuofei Qiao, Pengjun Xie, Fei Huang, Huajun Chen, Ningyu Zhang 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.

📄 PDF Abstract BibTeX arXiv:2508.06433

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MemPro: Agentic Memory Systems as Evolvable Programs

2026-05-30 · Qingshan Liu, Guoqing Wang, Wen Wu, Jingqi Huang 외 arxiv

Long-horizon autonomous agents require memory systems to retain historical information, track evolving states, and reuse relevant knowledge beyond finite context windows. Existing agentic memory systems typically follow …

MemPrivacy: Privacy-Preserving Personalized Memory Management for Edge-Cloud Agents

2026-05-10 · Yining Chen, Jihao Zhao, Bo Tang, Haofen Wang 외 arxiv

As LLM-powered agents are increasingly deployed in edge-cloud environments, personalized memory has become a key enabler of long-term adaptation and user-centric interaction. However, cloud-assisted memory management exp…

Information Extraction

MemPO: Self-Memory Policy Optimization for Long-Horizon Agents

2026-02-28 · Ruoran Li, Xinghua Zhang, Haiyang Yu, Shitong Duan 외 arxiv

Long-horizon agents face the challenge of growing context size during interaction with environment, which degrades the performance and stability. Existing methods typically introduce the external memory module and look u…

MEMPROBE: Probing Long-Term Agent Memory via Hidden User-State Recovery

2026-06-23 · Enze Ma, Yufan Zhou, Wei-Chieh Huang, Jie Yang 외 arxiv

Long-term memory promises LLM agents that grow more capable across sessions, maintaining an accurate, evolving understanding of the user that interaction forms. In practice, however, this memory is evaluated mostly throu…

MemPot: Defending Against Memory Extraction Attack with Optimized Honeypots

2026-02-07 · Yuhao Wang, Shengfang Zhai, Guanghao Jin, Yinpeng Dong 외 arxiv

Large Language Model (LLM)-based agents employ external and internal memory systems to handle complex, goal-oriented tasks, yet this exposes them to severe extraction attacks, and effective defenses remain lacking. In th…