用有限状态机自动构建多智能体系统，无需人工干预。
MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines
- 基于有限状态机自动生成多智能体架构
- 在文本与实际任务中表现接近人工设计水平
- 无需外部训练数据，通信结构灵活可优化
大型语言模型（LLMs）已在多智能体系统中展现出解决多种实际任务的能力。然而，现有手工设计的多智能体框架通常仅适用于预定义的小范围场景，而当前自动化设计方法存在工具集成不足、依赖外部训练数据以及通信结构僵化等局限。本文提出MetaAgent，一种基于有限状态机的自动构建框架。给定任务描述后，MetaAgent将生成多智能体系统，并通过优化算法进行打磨。部署时，有限状态机控制智能体行为与状态转移。我们在文本任务和实际任务上进行了实验，结果表明生成的多智能体系统优于其他自动化方法，并达到与针对特定任务优化的人工设计系统相当的性能。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have demonstrated the ability to solve a wide range of practical tasks within multi-agent systems. However, existing human-designed multi-agent frameworks are typically limited to a small set of pre-defined scenarios, while current automated design methods suffer from several limitations, such as the lack of tool integration, dependence on external training data, and rigid communication structures. In this paper, we propose MetaAgent, a finite state machine based framework that can automatically generate a multi-agent system. Given a task description, MetaAgent will design a multi-agent system and polish it through an optimization algorithm. When the multi-agent system is deployed, the finite state machine will control the agent's actions and the state transitions. To evaluate our framework, we conduct experiments on both text-based tasks and practical tasks. The results indicate that the generated multi-agent system surpasses other auto-designed methods and can achieve a comparable performance with the human-designed multi-agent system, which is optimized for those specific tasks.
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。