arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.04516cs.LG
收藏

多智能体流的在线联合微调

Online Joint Fine-tuning of Multi-Agent Flows

Microsoft Research(微软研究院)

Paul Mineiro

AI总结:

本文提出一种基于学习搜索框架的在线联合微调方法,用于优化多智能体流,并在Musique数据集上取得最先进结果。

摘要:

流(Flow)是由多个组件模型(“智能体”)组成的集合,通过迭代通信来构建复杂问题的解决方案。流已成为代码生成领域最先进的架构,也是Autogen等框架存在的理由。然而,当前流的构建依赖于手动提示工程和分阶段监督学习技术的结合;后者仅限于具有细粒度节点监督的无环流。在本文中,我描述了一种受“学习搜索”(Learning to Search)框架启发的整个流的在线联合微调过程。该方法利用模拟器访问,将整个情节的偏好简化为对单个节点输出的偏好;当组件是语言模型时,后者是一个已被充分研究的问题。如果情节评估器模型可用,该方法适用于无奖励设置(例如,文本反馈)。我将其应用于多跳问答数据集Musique,取得了最先进的结果。

英文摘要:

A Flow is a collection of component models ("Agents") which constructs the solution to a complex problem via iterative communication. Flows have emerged as state of the art architectures for code generation, and are the raison d'etre for frameworks like Autogen. However, flows are currently constructed via a combination of manual prompt engineering and stagewise supervised learning techniques; the latter is limited to acyclic flows with granular node supervision. In this writeup I describe a procedure for online joint fine-tuning of an entire flow inspired by the Learning to Search framework. The approach leverages simulator access to reduce preferences over entire episodes to preferences over individual node outputs; when the components are language models the latter is a well-studied problem. The approach is applicable to reward-free settings (e.g., text feedback) if an episode evaluator model is available. I apply to the multi-hop QA dataset Musique achieving a state-of-the-art result.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑