Beyond Self-Talk: A Communication-Centric Survey of LLM-Based Multi-Agent Systems
超越自我对话:基于LLM的多智能体系统的通信中心综述
机构 * School of Cyber Science and Technology, Beihang University, Beijing 100191, China(信息科学与技术学院,北京航空航天大学,北京100191,中国) ; The College of Cyber Security/College of Information Science and Technology, Jinan University, Guangzhou, China(网络安全学院/信息科学与技术学院,暨南大学,广州,中国) ; School of Computer Science and Engineering, Beihang University, Beijing 100083, China(计算机科学与工程学院,北京航空航天大学,北京100083,中国) ; School of Cyber Science and Technology, Beijing University of Posts and Telecommunications, Beijing 100876, China(信息科学与技术学院,北京邮电大学,北京100876,中国)
专题命中 多智能体 :agent(title,abstract);multi-agent(title,abstract);分类 cs.CL
AI总结 本文从通信视角综述基于大语言模型的多智能体系统,提出一个整合系统级和系统内部通信的结构化框架,分析智能体交互机制、挑战及未来方向。
Comments The article has been accepted by Frontiers of Computer Science (FCS), with the DOI: {10.1007/s11704-026-50857-y}