MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines
This addresses the need for more flexible and automated multi-agent systems in AI applications, though it appears incremental as it builds on existing automated design methods.
The paper tackles the problem of automatically constructing multi-agent systems, which are limited by human-designed frameworks and existing automated methods with issues like lack of tool integration and rigid communication. The result is MetaAgent, a framework that uses finite state machines to generate multi-agent systems, achieving performance comparable to human-designed systems in experiments on text-based and practical tasks.
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.