Large Language Model Multi-Agent Systems (LLM-MAS) have achieved great progress in solving complex tasks. It performs communication among agents within the system to collaboratively solve tasks, under the premise of shared information. However, when agents' collaborations are leveraged to perform multi-person tasks, a new challenge arises due to information asymmetry, since each agent can only access the information of its human user. Previous MAS struggle to complete tasks under this condition. To address this, we propose a new MAS paradigm termed iAgents, which denotes Informative Multi-Agent Systems. In iAgents, the human social network is mirrored in the agent network, where agents proactively exchange human information necessary for task resolution, thereby overcoming information asymmetry. iAgents employs a novel agent reasoning mechanism, InfoNav, to navigate agents' communication toward effective information exchange. Together with InfoNav, iAgents organizes human information in a mixed memory to provide agents with accurate and comprehensive information for exchange. Additionally, we introduce InformativeBench, the first benchmark tailored for evaluating LLM agents' task-solving ability under information asymmetry. Experimental results show that iAgents can collaborate within a social network of 140 individuals and 588 relationships, autonomously communicate over 30 turns, and retrieve information from nearly 70,000 messages to complete tasks within 3 minutes.
ComfyBench: Benchmarking LLM-based Agents in ComfyUI for Autonomously Designing Collaborative AI Systems
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Shanghai Jiao Tong University（上海交通大学）；The University of Sydney（悉尼大学）；The Chinese University of Hong Kong（香港中文大学）
AI Urban Scientist: Multi-Agent Collaborative Automation for Urban Research
Vanke School of Public Health, Tsinghua University, Beijing, China（范克学校公共卫生学院，清华大学，北京，中国）；Zhongguancun Academy, Beijing, China（中关村学院，北京，中国）；Department of Electronic Engineering, Tsinghua University, Beijing, China（电子工程系，清华大学，北京，中国）
Collaborative Trustworthiness for Good Decision Making in Autonomous Systems
Institute of Computer and Network Engineering (IDA) Technische Universität Braunschweig（计算机与网络工程学院（IDA） 拜鲁恩堡大学）；Chair of Embedded Systems TU Dortmund University（嵌入式系统教授 鄂尔敦大学）；Robert Bosch Corporate Research（博世企业研究）
Autonomous Collaborative Scheduling of Time-dependent UAVs, Workers and Vehicles for Crowdsensing in Disaster Response
School of Computer Science and Technology, Xidian University（西安电子科技大学计算机科学与技术学院）；College of Computer and Data Science, Fuzhou University（福州大学计算机与数据科学学院）；School of Computer Science, Northwestern Polytechnical University（西北工业大学计算机学院）；Harbin Engineering University（哈尔滨工程大学）
A collaborative agent with two lightweight synergistic models for autonomous crystal materials research
Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（中国科学院深圳先进技术研究院）；University of Chinese Academy of Sciences（中国科学院大学）；Institute for Advanced Study, Chengdu University（成都大学高等研究院）；Key Laboratory of Cyberspace Big Data Intelligent Security, Ministry of Education, Chongqing University of Posts and Telecommunications（重庆邮电大学教育部网络空间大数据智能安全重点实验室）
CP-Guard: Malicious Agent Detection and Defense in Collaborative Bird's Eye View Perception
City University of Hong Kong（香港城市大学）；University of Electronic Science and Technology of China（电子科技大学）；The University of Hong Kong（香港大学）；Lingnan University（岭南大学）
