Comments18 pages, 3 figures. Published at the Workshop on Agents in the Wild: Safety, Security, and Beyond (AIWILD) and the Workshop on Failure Modes of Agentic AI (FAGEN) at ICML 2026
机构
*
Tongji University(同济大学)
;
JD Explore Academy(京东探索研究院)
;
School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University(中山大学深圳校区网络科学与技术学院)
;
Berkeley AI Research Lab, University of California, Berkeley(加州大学伯克利分校伯克利人工智能研究实验室)
;
Technical University of Munich(慕尼黑工业大学)
Zhuoying Zhang, Ishan V. Prasad, Yuanzhe Hu, Zihang Liu, Hengrui Luo, Pu Ren, Yaoqing Yang
机构
*
Rice University(莱斯大学)
;
Dartmouth College(达特茅斯学院)
;
Georgia Institute of Technology(佐治亚理工学院)
;
University of California, Berkeley(加州大学伯克利分校)
;
Lawrence Berkeley National Laboratory(劳伦斯伯克利国家实验室)