Memp: Exploring Agent Procedural Memory
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917409796915200 |
|---|---|
| author | Fang, Runnan Liang, Yuan Wang, Xiaobin Wu, Jialong Qiao, Shuofei Xie, Pengjun Huang, Fei Chen, Huajun Zhang, Ningyu |
| author_facet | Fang, Runnan Liang, Yuan Wang, Xiaobin Wu, Jialong Qiao, Shuofei Xie, Pengjun Huang, Fei Chen, Huajun Zhang, Ningyu |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_06433 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Memp: Exploring Agent Procedural Memory Fang, Runnan Liang, Yuan Wang, Xiaobin Wu, Jialong Qiao, Shuofei Xie, Pengjun Huang, Fei Chen, Huajun Zhang, Ningyu Computation and Language Artificial Intelligence Machine Learning Multiagent Systems 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. |
| title | Memp: Exploring Agent Procedural Memory |
| topic | Computation and Language Artificial Intelligence Machine Learning Multiagent Systems |
| url | https://arxiv.org/abs/2508.06433 |