MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Ye, Rui, Tang, Shuo, Ge, Rui, Du, Yaxin, Yin, Zhenfei, Chen, Siheng, Shao, Jing
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912260747689984
author Ye, Rui
Tang, Shuo
Ge, Rui
Du, Yaxin
Yin, Zhenfei
Chen, Siheng
Shao, Jing
author_facet Ye, Rui
Tang, Shuo
Ge, Rui
Du, Yaxin
Yin, Zhenfei
Chen, Siheng
Shao, Jing
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2503_03686
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems
Ye, Rui
Tang, Shuo
Ge, Rui
Du, Yaxin
Yin, Zhenfei
Chen, Siheng
Shao, Jing
Computation and Language
Multiagent Systems
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.
title MAS-GPT: Training LLMs to Build LLM-based Multi-Agent Systems
topic Computation and Language
Multiagent Systems
url https://arxiv.org/abs/2503.03686