MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines

Yaolun Zhang, Xiaogeng Liu, Chaowei Xiao
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:75667-75694, 2025.

Abstract

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-zhang25bc, title = {{M}eta{A}gent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines}, author = {Zhang, Yaolun and Liu, Xiaogeng and Xiao, Chaowei}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {75667--75694}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/zhang25bc/zhang25bc.pdf}, url = {https://proceedings.mlr.press/v267/zhang25bc.html}, abstract = {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.} }
Endnote
%0 Conference Paper %T MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines %A Yaolun Zhang %A Xiaogeng Liu %A Chaowei Xiao %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-zhang25bc %I PMLR %P 75667--75694 %U https://proceedings.mlr.press/v267/zhang25bc.html %V 267 %X 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.
APA
Zhang, Y., Liu, X. & Xiao, C.. (2025). MetaAgent: Automatically Constructing Multi-Agent Systems Based on Finite State Machines. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:75667-75694 Available from https://proceedings.mlr.press/v267/zhang25bc.html.

Related Material