Guided Collaboration in Heterogeneous LLM-Based Multi-Agent Systems via Entropy-Based Understanding Assessment and Experience Retrieval
Faculty of Data Science, City University of Macau（数据科学学院，澳门城市大学）；Key Laboratory of Computing Power Network and Information Security, Ministry of Education, Shandong Computer Science Center, Qilu University of Technology (Shandong Academy of Sciences)（计算能力网络与信息安全重点实验室，教育部，山东计算机科学中心，齐鲁工业大学（山东科学院））；Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing, Shandong Fundamental Research Center for Computer Science（山东省计算能力互联网与服务计算重点实验室，山东省计算机科学基础研究中心）
With recent breakthroughs in large language models (LLMs) for reasoning, planning, and complex task generation, artificial intelligence systems are transitioning from isolated single-agent architectures to multi-agent systems with collaborative intelligence. However, in heterogeneous multi-agent systems (HMAS), capability differences among agents give rise to consistent cognitive problems, where strong and weak models fail to contribute effectively. We define the collaboration as a strong-weak system. Through comprehensive experiments, we disclose a counterintuitive phenomenon in the strong-weak system: a strong-weak collaboration may under-perform weak-weak combinations, revealing that cognitive mismatching are key bottlenecks limiting heterogeneous cooperation. To overcome these challenges, we propose an Entropy-Based Adaptive Guidance Framework that dynamically aligns the guidance with the cognitive state of each agent. The framework quantifies the understanding of weak agents through multi-dimensional entropy metrics - covering expression, uncertainty, structure, coherence, and relevance - and adaptively adjusts the intensity of the guidance at light, moderate and intensive levels. Furthermore, a Retrieval-Augmented Generation (RAG) mechanism is incorporated to retain successful collaboration experiences, enabling both immediate adaptation and long-term learning. Extensive experiments on three benchmark datasets, GSM8K, MBPP, and CVRP demonstrate that our approach consistently enhances the effectiveness and stability of heterogeneous collaboration. The results highlight that adaptive guidance not only mitigates cognitive imbalance but also establishes a scalable pathway toward more robust, cooperative multi-agent intelligence.
360$^\circ$REA: Towards A Reusable Experience Accumulation with 360° Assessment for Multi-Agent System
University of Electronic Science and Technology of China（电子科技大学）；Shandong University（山东大学）；Renmin University of China（中国人民大学）；National University of Defense Technology（国防科技大学）；Tsinghua University（清华大学）
Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration
Peking University（北京大学）；Shanghai Jiao Tong University（上海交通大学）；Tsinghua University（清华大学）；Beijing University of Posts and Telecommunications（北京邮电大学）；Siemens（西门子）；Tencent Robotics X（腾讯机器人实验室）
CoWork-X: Experience-Optimized Co-Evolution for Multi-Agent Collaboration System
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）科学与工程学院）；School of Artificial Intelligence, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）人工智能学院）；Tsinghua University（清华大学）；AutoGame Research（AutoGame研究）；Shenzhen Institute of Artificial Intelligence and Robotics for Society（深圳人工智能与机器人研究院）
StackPlanner: A Centralized Hierarchical Multi-Agent System with Task-Experience Memory Management
School of Computer Science, Peking University（北京大学计算机学院）；National Engineering Research Center for Software Engineering, Peking University（北京大学软件工程国家工程研究中心）；School of Public Affaris, Zhejiang University（浙江大学公共管理学院）；School of Software & Microelectronics, Peking University（北京大学软件与微电子学院）；GRG Banking Equipment Co., Ltd.（GRG银行设备有限公司）；Center on Frontiers of Computing Studies, Peking University（北京大学计算前沿中心）；Peking University Information Technology Institute (Tianjin Binhai)（北京大学信息技术研究院（天津滨海））
From Visual Perception to Deep Empathy: An Automated Assessment Framework for House-Tree-Person Drawings Using Multimodal LLMs and Multi-Agent Collaboration
Tsinghua University（清华大学）；Shenzhen University（深圳大学）；University of Oxford（牛津大学）；Shenzhen Institute of Education Sciences（深圳市教育科学研究院）；Guangzhou University of Chinese Medicine（广州中医药大学）；Harbin Institute of Technology（哈尔滨工业大学）
Bidirectional human-AI collaboration in brain tumour assessments improves both expert human and AI agent performance
University College London（伦敦大学学院）；National Hospital for Neurology and Neurosurgery（国立神经病学和神经外科医院）；NVIDIA（英伟达）；Great Ormond Street Hospital for Children（大奥蒙德街儿童医院）；Royal National Orthopaedic Hospital（皇家国立骨科医院）；University College Hospitals NHS Foundation Trust（伦敦大学学院医院国民保健服务基金会信托）；Royal Free Hospital（皇家自由医院）；Imperial College Healthcare NHS Trust（帝国理工学院医疗保健国民保健服务信托）；Imperial College London（帝国理工学院）
