Generative Flow Networks (GFlowNets) aim to generate diverse trajectories from a distribution in which the final states of the trajectories are proportional to the reward, serving as a powerful alternative to reinforcement learning for exploratory control tasks. However, the individual-flow matching constraint in GFlowNets limits their applications for multi-agent systems, especially continuous joint-control problems. In this paper, we propose a novel Multi-Agent generative Continuous Flow Networks (MACFN) method to enable multiple agents to perform cooperative exploration for various compositional continuous objects. Technically, MACFN trains decentralized individual-flow-based policies in a centralized global-flow-based matching fashion. During centralized training, MACFN introduces a continuous flow decomposition network to deduce the flow contributions of each agent in the presence of only global rewards. Then agents can deliver actions solely based on their assigned local flow in a decentralized way, forming a joint policy distribution proportional to the rewards. To guarantee the expressiveness of continuous flow decomposition, we theoretically derive a consistency condition on the decomposition network. Experimental results demonstrate that the proposed method yields results superior to the state-of-the-art counterparts and better exploration capability. Our code is available at https://github.com/isluoshuang/MACFN.
Creative Agents: Simulating the Systems Model of Creativity with Generative Agents
Graduate School of Engineering Science, Osaka University, Osaka, Japan(大阪大学工学研究科);Artificial Intelligence Exploration Research Center, The University of Electro-Communications, Tokyo, Japan(电通大学人工智能探索研究中心);International Research Center for Neurointelligence (WPI-IRCN), The University of Tokyo, Tokyo, Japan(东京大学神经智能国际研究中心)
EDU-MATRIX: A Society-Centric Generative Cognitive Digital Twin Architecture for Secondary Education
The High School Affiliated to Beijing Normal University(北京师范大学附属高中);Department of Electronic and Communication Engineering, North China Electric Power University(华北电力大学电子与通信工程系)
Grounded Answers for Multi-agent Decision-making Problem through Generative World Model
National Engineering Research Center for Visual Information and Application(国家视觉信息与应用工程研究中心);Institute of Artificial Intelligence and Robotics(人工智能与机器人研究所);Xi’an Jiaotong University(西安交通大学)
Emergence of Social Norms in Generative Agent Societies: Principles and Architecture
School of Mechanical Engineering, Northwestern Polytechnical University(西北工业大学机械工程学院);School of Cybersecurity, Northwestern Polytechnical University(西北工业大学网络空间安全学院);School of Artificial Intelligence, OPtics and ElectroNics(iOPEN), Northwestern Polytechnical University(西北工业大学人工智能、光学与电子学院(iOPEN));Shanghai Artificial Intelligence Laboratory(上海人工智能实验室)
Generative Multi-Agent Collaboration in Embodied AI: A Systematic Review
Tongji University(同济大学);East China Normal University(华东师范大学);Technical University of Munich(慕尼黑工业大学);Shanghai Research Institute for Intelligent Autonomous Systems, Tongji University(同济大学上海智能自主系统研究院);School of Computer Science and Technology, Tongji University(同济大学计算机科学与技术学院);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)
AINTMA: Agentic AI Architecture for Autonomous Test Management with Generative Intelligence, Secure Cloud Communication and Adaptive Quality Analytics
International Business Machines (IBM)(国际商业机器公司(IBM));Global Atlantic Financial(全球大西洋金融公司);Docusign(DocuSign公司);Salesforce Inc(Salesforce公司);The Home Depot(家得宝公司)
Assessing the Potential of Generative Agents in Crowdsourced Fact-Checking
Department of Electrical Engineering and Information Technology (DIETI), University of Naples Federico II(那不勒斯费德里科二世大学电气工程与信息技术系);Northwestern University, Department of Computer Science, McCormick School of Engineering and Applied Science(西北大学计算机科学系,麦科马克工程与应用科学学院)
Towards Urban Planing AI Agent in the Age of Agentic AI
University of Kansas(堪萨斯大学);University of Florida(佛罗里达大学);University of Central Florida(中央佛罗里达大学);University of Alabama(阿拉巴马大学);Arizona State University(亚利桑那州立大学)
Empowering Economic Simulation for Massively Multiplayer Online Games through Generative Agent-Based Modeling
State Key Laboratory of Cognitive Intelligence, University of Science and Technology of China(认知智能国家重点实验室,中国科学技术大学);NetEase Fuxi AI Lab(网易伏羲人工智能实验室);Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences(杭州高等研究院,中国科学院大学);National University of Singapore(新加坡国立大学);University of British Columbia(不列颠哥伦比亚大学)