TopoDIM: One-shot Topology Generation of Diverse Interaction Modes for Multi-Agent Systems

TL;DR

TopoDIM introduces a one-shot, diverse topology generation framework for multi-agent systems that enhances efficiency and adaptability without iterative communication, outperforming existing methods in token consumption and task performance.

Contribution

It presents a novel decentralized approach for autonomous, heterogeneous communication topology construction in multi-agent systems, reducing latency and computation.

Findings

Reduces total token consumption by 46.41%.

Improves average task performance by 1.50%.

Demonstrates strong adaptability in heterogeneous agent communication.

Abstract

Optimizing communication topology in LLM-based multi-agent system is critical for enabling collective intelligence. Existing methods mainly rely on spatio-temporal interaction paradigms, where the sequential execution of multi-round dialogues incurs high latency and computation. Motivated by the recent insights that evaluation and debate mechanisms can improve problem-solving in multi-agent systems, we propose TopoDIM, a framework for one-shot Topology generation with Diverse Interaction Modes. Designed for decentralized execution to enhance adaptability and privacy, TopoDIM enables agents to autonomously construct heterogeneous communication without iterative coordination, achieving token efficiency and improved task performance. Experiments demonstrate that TopoDIM reduces total token consumption by 46.41% while improving average performance by 1.50% over state-of-the-art methods. Moreover, the framework exhibits strong adaptability in organizing communication among heterogeneous agents. Code is available at: https://github.com/Sundiasy/TopoDIM.