In 2021 the Johns Hopkins University Applied Physics Laboratory held an internal challenge to develop artificially intelligent (AI) agents that could excel at the collaborative card game Hanabi. Agents were evaluated on their ability to play with human players whom the agents had never previously encountered. This study details the development of the agent that won the challenge by achieving a human-play average score of 16.5, outperforming the current state-of-the-art for human-bot Hanabi scores. The winning agent's development consisted of observing and accurately modeling the author's decision making in Hanabi, then training with a behavioral clone of the author. Notably, the agent discovered a human-complementary play style by first mimicking human decision making, then exploring variations to the human-like strategy that led to higher simulated human-bot scores. This work examines in detail the design and implementation of this human compatible Hanabi teammate, as well as the existence and implications of human-complementary strategies and how they may be explored for more successful applications of AI in human machine teams.
Evaluation of Human-AI Teams for Learned and Rule-Based Agents in Hanabi
MIT Lincoln Laboratory（麻省理工学院林肯实验室）；MIT Department of Electrical Engineering and Computer Science（麻省理工学院电气工程与计算机科学系）；U.S. Air Force Artificial Intelligence Accelerator（美国空军人工智能加速器）
Symmetry-Breaking Augmentations for Ad Hoc Teamwork
Foerster Lab for AI Research, University of Oxford（牛津大学人工智能研究实验室）；Australian Institute for Machine Learning, University of Adelaide（阿德莱德大学人工智能研究所）；Meta AI Research, UK（英国Meta人工智能研究）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
DeepTrans Studio: Turning Expert Interventions into Shared Team Knowledge in Agentic Translation Workflows
School of Computer Engineering and Science, Shanghai University（上海大学计算机工程与科学学院）；School of Foreign Languages, East China Normal University（华东师范大学外国语言学系）；School of Foreign Studies, Shanghai University（上海大学外国语言学院）；Department of Computer Science and Engineering, Shanghai Jiao Tong University（上海交通大学计算机科学与工程学院）
Generalizable Agent Modeling for Agent Collaboration-Competition Adaptation with Multi-Retrieval and Dynamic Generation
Beijing University of Posts and Telecommunications（北京邮电大学）；Beijing Institute of Technology（北京理工大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Tsinghua University（清华大学）
A study on human-agent teaming through spoken interaction: the impact of human individual traits and agent characteristics
Instituto de Investigación en Ciencias de la Computación, UBA-CONICET（布宜诺斯艾利斯大学-国家科学技术研究委员会计算机科学研究所）；Departamento de Computación, Facultad de Ciencias Exactas y Naturales, Universidad de Buenos Aires（布宜诺斯艾利斯大学精确与自然科学学院计算机系）；Universidad Nacional de Córdoba（科尔多瓦国立大学）；Instituto de Educación, Universidad Nacional de Hurlingham, UNAHUR-CONICET（Hurlingham国立大学-国家科学技术研究委员会教育研究所）
FedPOB: Sample-Efficient Federated Prompt Optimization via Bandits
The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；South China University of Technology（华南理工大学）；University of Edinburgh（爱丁堡大学）；Beihang University（北航）；The Hong Kong University of Science and Technology (Guangzhou)（香港科学与技术大学（广州））；East China Normal University（华东师范大学）；City University of Hong Kong（香港城市大学）
Why Human Guidance Matters in Collaborative Vibe Coding
Cornell University（康奈尔大学）；Princeton University（普林斯顿大学）；Massachusetts Institute of Technology（麻省理工学院）；University of Cambridge（剑桥大学）；New York University（纽约大学）
L2M-AID: Autonomous Cyber-Physical Defense by Fusing Semantic Reasoning of Large Language Models with Multi-Agent Reinforcement Learning (Preprint)
Peking University（北京大学）；RWTH Aachen University（亚琛工业大学）；University of Texas at Austin（德克萨斯大学奥斯汀分校）；Wuhan University（武汉大学）；Thales Group（泰雷兹集团）；Chinese Medical Information and Big Data Association（中国医学信息与大数据协会）
