让大模型一键生成自适应多智能体系统，省去人工配置。
MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems
- 将构建多智能体系统视为生成任务，输入问题输出对应系统。
- 在9个基准上优于10+基线方法，单次推理即可生成有效系统。
- 适合想快速搭建高效多智能体系统的研究人员和开发者。
基于大模型的多智能体系统（MAS）在处理多样化任务方面展现出巨大潜力。然而，现有方法高度依赖人工配置或多次调用高级大模型，导致适应性差且推理成本高。本文将构建MAS的过程重构为生成式语言任务：输入为用户查询，输出为对应的MAS。为此，我们统一将MAS表示为可执行代码，并提出一致性导向的数据构建流程，生成高质量的查询-MAS配对数据集。基于该数据集，训练出开源中等规模的大模型MAS-GPT，可在一次推理中生成适配查询的MAS。生成的MAS可无缝用于处理用户请求并输出高质量响应。在9个基准和5个大模型上的实验表明，MAS-GPT在多种设置下均持续优于10多个基线方法，证明其高效、有效且具备强泛化能力。代码将发布于https://github.com/rui-ye/MAS-GPT。
原文摘要 · Abstract (English)
LLM-based multi-agent systems (MAS) have shown significant potential in tackling diverse tasks. However, to design effective MAS, existing approaches heavily rely on manual configurations or multiple calls of advanced LLMs, resulting in inadaptability and high inference costs. In this paper, we simplify the process of building an MAS by reframing it as a generative language task, where the input is a user query and the output is a corresponding MAS. To address this novel task, we unify the representation of MAS as executable code and propose a consistency-oriented data construction pipeline to create a high-quality dataset comprising coherent and consistent query-MAS pairs. Using this dataset, we train MAS-GPT, an open-source medium-sized LLM that is capable of generating query-adaptive MAS within a single LLM inference. The generated MAS can be seamlessly applied to process user queries and deliver high-quality responses. Extensive experiments on 9 benchmarks and 5 LLMs show that the proposed MAS-GPT consistently outperforms 10+ baseline MAS methods on diverse settings, indicating MAS-GPT's high effectiveness, efficiency and strong generalization ability. Code will be available at https://github.com/rui-ye/MAS-GPT.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。