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

TL;DR

This paper introduces ARG-Designer, a novel autoregressive graph generation model that automatically designs multi-agent communication topologies tailored to specific tasks, outperforming existing methods in flexibility and efficiency.

Contribution

It reframes MAS design as a conditional autoregressive graph generation task and proposes ARG-Designer to construct customized collaboration graphs from scratch.

Findings

Achieves state-of-the-art performance on six benchmarks.

Demonstrates greater token efficiency than existing approaches.

Provides highly extensible and task-specific communication topologies.

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.