Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems

2025-05-28

AI Summary

This study addresses the problem of designing optimal topologies for large language model (LLM)-driven multi-agent systems (MAS), a challenge hitherto unexplored in a systematic manner—particularly regarding how agent organization impacts collaborative performance. To this end, we propose the “topology-aware MAS” paradigm and introduce a three-stage learning framework encompassing agent selection, structural characterization, and topology synthesis. Methodologically, our approach integrates LLMs, graph neural networks, reinforcement learning, and generative modeling to enable dynamic relation discovery, communication pattern optimization, and self-evolving topology adaptation. Our contribution is the first realization of learnable, task-adaptive MAS architectures, yielding significant improvements in collaboration efficiency and substantial reduction in redundancy. The methodology supports high-cohesion, low-overhead deployment of MAS in real-world applications and establishes both theoretical foundations and practical technical pathways for structured multi-agent system research.

Technology Category

• Multiagent Systems: Multiagent Learning
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Large Language Model-based Multi-Agent Systems (MASs) have emerged as a powerful paradigm for tackling complex tasks through collaborative intelligence. Nevertheless, the question of how agents should be structurally organized for optimal cooperation remains largely unexplored. In this position paper, we aim to gently redirect the focus of the MAS research community toward this critical dimension: develop topology-aware MASs for specific tasks. Specifically, the system consists of three core components - agents, communication links, and communication patterns - that collectively shape its coordination performance and efficiency. To this end, we introduce a systematic, three-stage framework: agent selection, structure profiling, and topology synthesis. Each stage would trigger new research opportunities in areas such as language models, reinforcement learning, graph learning, and generative modeling; together, they could unleash the full potential of MASs in complicated real-world applications. Then, we discuss the potential challenges and opportunities in the evaluation of multiple systems. We hope our perspective and framework can offer critical new insights in the era of agentic AI.

Problem

• Exploring optimal structural organization for LLM-based multi-agent cooperation
• Developing topology-aware MASs to enhance coordination performance and efficiency
• Addressing challenges in evaluating multi-agent systems for real-world applications

Innovation

• Develop topology-aware MASs for tasks
• Three-stage framework for MAS optimization
• Combine language models and graph learning