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

2026-01-15

AI Summary

This work proposes TopoDIM, a novel framework that addresses the high latency and computational overhead inherent in traditional multi-agent systems, which rely on iterative spatiotemporal interactions to achieve collective intelligence. TopoDIM enables one-shot generation of diverse communication topologies, allowing decentralized agents to autonomously establish heterogeneous interaction patterns without requiring multiple rounds of coordination. The approach integrates large language models, decentralized architectures, and topology generation techniques, enhanced by an evaluation-and-debate mechanism that guides the design of effective topologies. Experimental results demonstrate that TopoDIM reduces total token consumption by 46.41% compared to existing methods while improving average task performance by 1.50%, significantly enhancing the system’s self-organizing capability and communication adaptability in heterogeneous environments.

Technology Category

• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Decentralized Web and Fediverse systems
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystems

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://anonymous.4open.science/r/TopoDIM-8D35/

Problem

• multi-agent systems
• communication topology
• interaction modes
• token efficiency
• collective intelligence

Innovation

• one-shot topology generation
• diverse interaction modes
• multi-agent systems
• decentralized execution
• token efficiency