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

TL;DR

This paper advocates for a focus on the topology of Large Language Model-based Multi-Agent Systems, proposing a systematic framework to optimize agent interactions for improved system performance.

Contribution

It introduces a three-stage framework for designing and optimizing MAS topologies, emphasizing the importance of topology-aware configurations in agent systems.

Findings

Framework enables systematic topology design

Highlights importance of agent interaction structure

Opens new research directions in MAS optimization

Abstract

Large Language Model-based Multi-Agent Systems (MASs) have emerged as a powerful paradigm for tackling complex tasks through collaborative intelligence. However, the topology of these systems--how agents in MASs should be configured, connected, and coordinated--remains largely unexplored. In this position paper, we call for a paradigm shift toward \emph{topology-aware MASs} that explicitly model and dynamically optimize the structure of inter-agent interactions. We identify three fundamental components--agents, communication links, and overall topology--that collectively determine the system's adaptability, efficiency, robustness, and fairness. To operationalize this vision, we introduce a systematic three-stage framework: 1) agent selection, 2) structure profiling, and 3) topology synthesis. This framework not only provides a principled foundation for designing MASs but also opens new research frontiers across language modeling, reinforcement learning, graph learning, and generative modeling to ultimately unleash their full potential in complex real-world applications. We conclude by outlining key challenges and opportunities in MASs evaluation. We hope our framework and perspectives offer critical new insights in the era of agentic AI.