Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Li, Shiyuan, Liu, Yixin, Wen, Qingsong, Zhang, Chengqi, Pan, Shirui
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912718059995136
author Li, Shiyuan
Liu, Yixin
Wen, Qingsong
Zhang, Chengqi
Pan, Shirui
author_facet Li, Shiyuan
Liu, Yixin
Wen, Qingsong
Zhang, Chengqi
Pan, Shirui
contents Multi-agent systems (MAS) based on large language models (LLMs) have emerged as a powerful solution for dealing with complex problems across diverse domains. The effectiveness of MAS is critically dependent on its collaboration topology, which has become a focal point for automated design research. However, existing approaches are fundamentally constrained by their reliance on a template graph modification paradigm with a predefined set of agents and hard-coded interaction structures, significantly limiting their adaptability to task-specific requirements. To address these limitations, we reframe MAS design as a conditional autoregressive graph generation task, where both the system composition and structure are designed jointly. We propose ARG-Designer, a novel autoregressive model that operationalizes this paradigm by constructing the collaboration graph from scratch. Conditioned on a natural language task query, ARG-Designer sequentially and dynamically determines the required number of agents, selects their appropriate roles from an extensible pool, and establishes the optimal communication links between them. This generative approach creates a customized topology in a flexible and extensible manner, precisely tailored to the unique demands of different tasks. Extensive experiments across six diverse benchmarks demonstrate that ARG-Designer not only achieves state-of-the-art performance but also enjoys significantly greater token efficiency and enhanced extensibility. The source code of ARG-Designer is available at https://github.com/Shiy-Li/ARG-Designer.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18224
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation
Li, Shiyuan
Liu, Yixin
Wen, Qingsong
Zhang, Chengqi
Pan, Shirui
Multiagent Systems
Computation and Language
Multi-agent systems (MAS) based on large language models (LLMs) have emerged as a powerful solution for dealing with complex problems across diverse domains. The effectiveness of MAS is critically dependent on its collaboration topology, which has become a focal point for automated design research. However, existing approaches are fundamentally constrained by their reliance on a template graph modification paradigm with a predefined set of agents and hard-coded interaction structures, significantly limiting their adaptability to task-specific requirements. To address these limitations, we reframe MAS design as a conditional autoregressive graph generation task, where both the system composition and structure are designed jointly. We propose ARG-Designer, a novel autoregressive model that operationalizes this paradigm by constructing the collaboration graph from scratch. Conditioned on a natural language task query, ARG-Designer sequentially and dynamically determines the required number of agents, selects their appropriate roles from an extensible pool, and establishes the optimal communication links between them. This generative approach creates a customized topology in a flexible and extensible manner, precisely tailored to the unique demands of different tasks. Extensive experiments across six diverse benchmarks demonstrate that ARG-Designer not only achieves state-of-the-art performance but also enjoys significantly greater token efficiency and enhanced extensibility. The source code of ARG-Designer is available at https://github.com/Shiy-Li/ARG-Designer.
title Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation
topic Multiagent Systems
Computation and Language
url https://arxiv.org/abs/2507.18224