{"ID":2890829,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.18224","arxiv_id":"2507.18224","title":"Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation","abstract":"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.","short_abstract":"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 ap...","url_abs":"https://arxiv.org/abs/2507.18224","url_pdf":"https://arxiv.org/pdf/2507.18224v4","authors":"[\"Shiyuan Li\",\"Yixin Liu\",\"Qingsong Wen\",\"Chengqi Zhang\",\"Shirui Pan\"]","published":"2025-07-24T09:17:41Z","proceeding":"cs.MA","tasks":"[\"cs.MA\",\"cs.CL\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false,"code_links":[{"ID":611812,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2890829,"paper_url":"https://arxiv.org/abs/2507.18224","paper_title":"Assemble Your Crew: Automatic Multi-agent Communication Topology Design via Autoregressive Graph Generation","repo_url":"https://github.com/Shiy-Li/ARG-Designer","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}