返回全部动态
XferAgent：面向自改进LLM智能体的跨智能体经验迁移
原标题：XferAgent: Cross-Agent Experience Transfer for Self-Improving LLM Agents
AI 摘要
该论文提出 XferAgent 框架，用于异构 LLM 智能体之间的跨智能体经验迁移。它通过本地经验图和共享经验图组织可复用经验，并借助跨智能体经验协调、任务条件经验路由和本地-共享经验整合，选择与新任务相关的经验。实验表明，该方法在多种任务和 LLM 基座上优于代表性记忆方法，并支持跨框架经验复用，随着任务重复执行，累计任务成功率逐步提升。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
XferAgent: Cross-Agent Experience Transfer for Self-Improving LLM Agents 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 i
发布时间：2026-10-15 12:00
抓取时间：2026-10-15 12:46
来源机构：arXiv