AI agents powered by Large Language Models (LLMs) have made significant advances, enabling them to assist humans in diverse complex tasks and leading to a revolution in human-AI coordination. LLM-powered agents typically require invoking LLM APIs and employing artificially designed complex prompts, which results in high inference latency. While this paradigm works well in scenarios with minimal interactive demands, such as code generation, it is unsuitable for highly interactive and real-time applications, such as gaming. Traditional gaming AI often employs small models or reactive policies, enabling fast inference but offering limited task completion and interaction abilities. In this work, we consider Overcooked as our testbed where players could communicate with natural language and cooperate to serve orders. We propose a Hierarchical Language Agent (HLA) for human-AI coordination that provides both strong reasoning abilities while keeping real-time execution. In particular, HLA adopts a hierarchical framework and comprises three modules: a proficient LLM, referred to as Slow Mind, for intention reasoning and language interaction, a lightweight LLM, referred to as Fast Mind, for generating macro actions, and a reactive policy, referred to as Executor, for transforming macro actions into atomic actions. Human studies show that HLA outperforms other baseline agents, including slow-mind-only agents and fast-mind-only agents, with stronger cooperation abilities, faster responses, and more consistent language communications.
TreeReader: A Hierarchical Academic Paper Reader Powered by Language Models
University of Toronto(多伦多大学);Vector Institute for Artificial Intelligence(向量人工智能研究所);University of Toronto Mississauga(多伦多大学密西沙加分校);Acceleration Consortium(加速联盟);Canadian Institute for Advanced Research (CIFAR)(加拿大高级研究院);NVIDIA(英伟达)
HAVEN: Hierarchical Cooperative Multi-Agent Reinforcement Learning with Dual Coordination Mechanism
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
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))
Stackelberg Decision Transformer for Asynchronous Action Coordination in Multi-Agent Systems
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);SenseTime Research(商汤科技研究院)
ReflecSched: Solving Dynamic Flexible Job-Shop Scheduling via LLM-Powered Hierarchical Reflection
School of Computer Science and Engineering(计算机科学与工程学院);Beihang University(北京航空航天大学);Qingdao Research Institute(青岛研究院);Hangzhou Innovation Institute(杭州创新研究院);Zhongguancun Laboratory(中关村实验室)
AgentRec: Next-Generation LLM-Powered Multi-Agent Collaborative Recommendation with Adaptive Intelligence
Department of Software \& Microelectronics Peking University Beijing, China;Department of Software \& Microelectronics Peking University Beijing, China hangli\;Department of Software \& Microelectronics Peking University Beijing, China zehua\;Department of Software \& Microelectronics Peking University Beijing, China xiaofan\;Economic Law School China University of Political Science;School of Computer Science Peking University Beijing, China
Multi-Agent Coordination across Diverse Applications: A Survey
Shenzhen Technology University(深圳技术大学);Tencent(腾讯);Southern University of Science and Technology(南方科技大学);Southwest University(西南大学);University of Technology Sydney(悉尼科技大学)
Hierarchical Reinforcement Learning in StarCraft Micromanagement with Influence Maps and Cluster-based Scripts
School of Artificial Intelligence and Automation, China University of Geosciences, Wuhan(中国地质大学(武汉)人工智能与自动化学院);State Key Laboratory of Digital Intelligent Technology for Unmanned Coal Mining, Anhui University of Science & Technology, Huainan(安徽省科学技术大学无人煤矿数字智能技术重点实验室);Hubei Key Laboratory of Advanced Control and Intelligent Automation for Complex Systems, Wuhan(湖北省复杂系统先进控制与智能自动化重点实验室);Engineering Research Center of Intelligent Technology for Geo-Exploration, Ministry of Education, Wuhan(地质探测智能技术工程研究中心,教育部,武汉);School of Artificial Intelligence, Anhui University of Science & Technology, Hefei(安徽省科学技术大学人工智能学院);Computer Science and Informatics, De Montfort University, Leicester, U.K.(德蒙福特大学计算机科学与信息学)
Before Humans Join the Team: Diagnosing Coordination Failures in Healthcare Robot Team Simulation
Cornell Tech(康奈尔科技校区);Department of Information Science, Cornell University(康奈尔大学信息科学系);University of Maryland, College Park(马里兰大学帕克分校);Imperial College London(伦敦帝国学院)
HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via Learned Messaging
IIIT-Bangalore(班加罗尔国际信息技术研究所);Ericsson Research(爱立信研究院);IIT-BHU(贝拿勒斯印度教大学印度理工学院);University of Alberta(阿尔伯塔大学);Alberta Machine Intelligence Institute (Amii)(阿尔伯塔机器智能研究所)