ChannelGuard: Safe Models Do Not Compose into Safe Multi-Agent Systems
通道卫士:安全模型无法组合成安全的多智能体系统
Elias Hossain, Md Mehedi Hasan Nipu, Fatema Tuj Johora Faria, Tasfia Nuzhat Ornee, Maleeha Sheikh
机构
*
College of Engineering and Computer Science, University of Central Florida(工程与计算机科学学院,中央佛罗里达大学)
;
Department of Computer Science and Engineering, North South University(计算机科学与工程系,北南大学)
;
Computer Science and Engineering, Ahsanullah University of Science and Technology(计算机科学与工程,阿沙努拉科学与技术大学)
;
Department of Electrical and Computer Engineering, Purdue University Fort Wayne(电气与计算机工程系,普渡大学弗拉特沃恩分校)
机构
*
East China Normal University(东华大学)
;
Hefei University of Technology(合肥工业大学)
;
China University of Petroleum(中国石油大学)
;
Guangdong university of Finance & Economics(广东财经大学)
;
Alibaba Group(阿里巴巴集团)
CommentsCritical flaw in Eq.(5)/Alg.1 (Sec 3.2): scoring fails Lipschitz continuity in multi-modal spaces, causing invalid hierarchy. Thus, latency/FLOPs in Tables 2&3 are overestimated & irreproducible. Core defect unfixable by minor update. Withdraw to avoid misleading; will revise theory & experiments
Comments14 pages, 4 figures, 4 tables, 1 demo-video and repository link. There were major changes: an introduction, a review, and a new experiment. Some tables and figures have also been changed
Communication-Enhanced Tutoring for Efficient Decentralized Multi-Agent Reinforcement Learning
MACTAS: 基于自注意力的多智能体强化学习中智能体间通信方法 with 动作-价值函数分解
Maciej Wojtala, Bogusz Stefańczyk, Dominik Bogucki, Łukasz Lepak, Paweł Wawrzyński
机构
*
University of Warsaw(华沙大学)
;
IDEAS Research Institute(IDEAS研究机构)
;
Institute of Fundamental Technological Research, Polish Academy of Sciences(波兰科学院基础技术研究所)
;
IDEAS NCBR
;
Warsaw University of Technology(华沙技术大学)
Embedded Universal Predictive Intelligence: a coherent framework for multi-agent learning
嵌入式通用预测智能:多智能体学习的统一框架
Alexander Meulemans, Rajai Nasser, Maciej Wołczyk, Marissa A. Weis, Seijin Kobayashi, Blake Richards, Guillaume Lajoie, Angelika Steger, Marcus Hutter, James Manyika, Rif A. Saurous, João Sacramento, Blaise Agüera y Arcas
机构
*
Peking University(北京大学)
;
University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
;
University of Pennsylvania(宾夕法尼亚大学)
;
Purdue University(普渡大学)
;
Stanford University(斯坦福大学)
A Multi-Agent System for Motor Design Optimization via an FEA-AI Hybrid Approach
基于FEA-AI混合方法的IPMSM设计优化多智能体系统
Jinseong Han, Sunwoong Yang, Namwoo Kang
机构
*
Cho Chun Shik Graduate School of Mobility, KAIST(KAIST Cho Chun Shik 移动研究生院)
;
Department of Mechanical Engineering, Hanyang University(汉阳大学机械工程系)
;
Narnia Labs
Comments8 pages (9 more for appendix), 3 figures. Published at the Second Workshop on Agents in the Wild: Safety, Security, and Beyond (AIWILD) at ICML 2026
The Capability Paradox: How Smarter Auditors Make Multi-Agent Systems Less Secure
能力悖论:更聪明的审计员如何使多智能体系统更不安全
Qiqi Liu, Runhan Song, Shilin Ye
机构
*
University of Chinese Academy of Sciences(中国科学院大学)
;
Max Planck Institute for Security and Privacy(马克斯·普朗克安全与隐私研究所)
;
Henan Yinzhu Safety Technology Co., Ltd.(河南亿众安全技术有限公司)
;
Harbin Institute of Technology, Faculty of Computing(哈尔滨工业大学计算机学院)
Multi-agent DRL-based Lane Change Decision Model for Cooperative Platooning in Mixed Traffic
基于多智能体深度强化学习的车道变换决策模型:用于混合交通中协同规划
Zeyu Mu, Shangtong Zhang, B. Brian Park
机构
*
University of Virginia(弗吉尼亚大学)
;
Link Lab(链接实验室)
;
Department of Systems and Information Engineering(系统与信息工程系)
;
Department of Computer Science(计算机科学系)