arXiv cs.MA· Weihao Li, Jun Bai, Shijie Chen, Qincheng Lu, Xinyu Wang, Ziyang Song·· 4 天前AI 评分22
XferAgent：面向自我改进 LLM 智能体的跨智能体经验迁移框架
XferAgent: Cross-Agent Experience Transfer for Self-Improving LLM Agents
AI 导读
XferAgent 是一个跨智能体经验迁移框架，通过本地与共享经验图组织可复用经验，调和异构智能体的兼容贡献并避免不可靠合并。它为新任务挑选共享经验并与目标智能体的本地经验整合，在多种任务域上优于代表性记忆类方法，并实现异构智能体框架间的有效经验迁移，随着智能体更新和复用经验，累计任务成功率在连续任务轮次中持续提升。
正文 · 原文
Abstract:Large language model (LLM) agents can reuse experience from prior task executions to improve performance on subsequent tasks. Although existing methods enable cross-agent experience sharing, differences in agents' execution histories and task requirements make shared experiences difficult to reuse effectively. We propose XferAgent, a framework for cross-agent experience transfer that organizes reusable experience in local and shared experience graphs. XferAgent reconciles compatible contributions from heterogeneous agents while avoiding unreliable merges. For each new task, it selects shared experiences and integrates them with the target agent's local experience to support task execution. Experiments across diverse task domains show improvements over representative memory-based methods and effective experience transfer between heterogeneous agent frameworks. Cumulative task success also increases over successive task passes as agents update and reuse their experiences.
| Comments: | 14 pages |
| Subjects: | Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.19581 [cs.MA] |
| (or arXiv:2610.19581v1 [cs.MA] for this version) | |
| https://doi.org/10.48550/arXiv.2610.19581 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jun Bai [view email]
[v1]
Wed, 14 Oct 2026 04:51:53 UTC (1,154 KB)
来源：arXiv cs.MA · arxiv.org