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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Yang, Jiaxi, Zhang, Mengqi, Jin, Yiqiao, Chen, Hao, Wen, Qingsong, Lin, Lu, He, Yi, Kumar, Srijan, Xu, Weijie, Evans, James, Wang, Jindong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912653342932992
author Yang, Jiaxi
Zhang, Mengqi
Jin, Yiqiao
Chen, Hao
Wen, Qingsong
Lin, Lu
He, Yi
Kumar, Srijan
Xu, Weijie
Evans, James
Wang, Jindong
author_facet Yang, Jiaxi
Zhang, Mengqi
Jin, Yiqiao
Chen, Hao
Wen, Qingsong
Lin, Lu
He, Yi
Kumar, Srijan
Xu, Weijie
Evans, James
Wang, Jindong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_22467
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems
Yang, Jiaxi
Zhang, Mengqi
Jin, Yiqiao
Chen, Hao
Wen, Qingsong
Lin, Lu
He, Yi
Kumar, Srijan
Xu, Weijie
Evans, James
Wang, Jindong
Multiagent Systems
Artificial Intelligence
Machine Learning
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.
title Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems
topic Multiagent Systems
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2505.22467