GoAgent: Group-of-Agents Communication Topology Generation for LLM-based Multi-Agent Systems
School of Cyberspace, Hangzhou Dianzi University(杭州电子科技大学信息学院);School of Computing Technologies, RMIT University(皇家墨尔本理工大学计算技术学院);School of Information and Communication Technology, Griffith University(格里菲斯大学信息与通信技术学院)
Hongjiang Chen, Xin Zheng, Yixin Liu, Pengfei Jiao, Shiyuan Li, Huan Liu, Zhidong Zhao, Ziqi Xu, Ibrahim Khalil, Shirui Pan
Large language model (LLM)-based multi-agent systems (MAS) have demonstrated exceptional capabilities in solving complex tasks, yet their effectiveness depends heavily on the underlying communication topology that coordinates agent interactions. Within these systems, successful problem-solving often necessitates task-specific group structures to divide and conquer subtasks. However, most existing approaches generate communication topologies in a node-centric manner, leaving group structures to emerge implicitly from local connectivity decisions rather than modeling them explicitly, often leading to suboptimal coordination and unnecessary communication overhead. To address this limitation, we propose GoAgent (Group-of-Agents), a communication topology generation method that explicitly treats collaborative groups as the atomic units of MAS construction. Specifically, GoAgent first enumerates task-relevant candidate groups through an LLM and then autoregressively selects and connects these groups as atomic units to construct the final communication graph, jointly capturing intra-group cohesion and inter-group coordination. To mitigate communication redundancy and noise propagation inherent in expanding topologies, we further introduce a conditional information bottleneck (CIB) objective that compresses inter-group communication, preserving task-relevant signals while filtering out redundant historical noise. Extensive experiments on six benchmarks demonstrate the state-of-the-art performance of GoAgent with 93.84% average accuracy while reducing token consumption by about 17%.
Goal-Oriented Multi-Agent Semantic Networking: Unifying Intents, Semantics, and Intelligence
Department of Engineering, King’s College London(伦敦国王学院工程系);Network Automation Department, NSSR Lab, Nokia Bell Labs(诺基亚贝尔实验室网络自动化部门);Bristol Research and Innovation Laboratory, Toshiba Europe Ltd.(东芝欧洲有限公司布里斯托尔研究与创新实验室)
Exponential Topology-enabled Scalable Communication in Multi-agent Reinforcement Learning
The Hong Kong University of Science and Technology(香港科技大学);Institute of Artificial Intelligence (TeleAI), China Telecom(中国电信人工智能研究院(TeleAI));Software Engineering Institute, East China Normal University(华东师范大学软件工程学院)
Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference
University of Chinese Academy of Sciences(中国科学院大学);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所);Beijing University of Posts and Telecommunications(北京邮电大学)
Understanding the Information Propagation Effects of Communication Topologies in LLM-based Multi-Agent Systems
School of Artificial Intelligence, Jilin University, Changchun, China(吉林大学人工智能学院);School of Information and Communication Technology, Griffith University, Goldcoast, Australia(格里菲斯大学信息与通信技术学院);School of Computer Science and Engineering, University of New South Wales, Sydney, Australia(新南威尔士大学计算机科学与工程学院)
CIA: Inferring the Communication Topology from LLM-based Multi-Agent Systems
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络安全学院);Griffith University(格里菲斯大学);Nanyang Technological University(南洋理工大学);Academy of Mathematics and Systems Science, Chinese Academy of Sciences(中国科学院数学与系统科学研究院)
DyTopo: Dynamic Topology Routing for Multi-Agent Reasoning via Semantic Matching
Peking University, Beijing, China(北京大学);Georgia Institute of Technology, Atlanta, United States(佐治亚理工学院);Southeast University, Location, Country(东南大学);Tsinghua University(清华大学)
Learning Structured Communication for Multi-agent Reinforcement Learning
School of Computer Science and Technology, East China Normal University(华东师范大学计算机科学与技术学院);Department of Computer Science and Engineering, Artificial Intelligence Institute, Shanghai Jiao Tong University(上海交通大学计算机科学与工程系人工智能研究所);School of Science and Engineering, The Chinese University of Hong Kong (Shenzhen)(香港中文大学(深圳)理工学院);School of Computational Science and Engineering, College of Computing, Georgia Institute of Technology(佐治亚理工学院计算学院计算科学与工程学院)
Leveraging Communication Topologies Between Learning Agents in Deep Reinforcement Learning
Massachusetts Institute of Technology(麻省理工学院);MILA/Université de Montréal(蒙特利尔学习算法研究所/蒙特利尔大学);Universidad Carlos III de Madrid(马德里卡洛斯三世大学);Oxford Internet Institute, University of Oxford(牛津大学互联网研究所)