LoopTrap: Termination Poisoning Attacks on LLM Agents
LoopTrap: 对 LLM agent 的终止污染攻击
Huiyu Xu, Zhibo Wang, Wenhui Zhang, Ziqi Zhu, Yaopeng Wang, Kui Ren, Chun Chen
机构
*
The State Key Laboratory of Blockchain and Data Security(区块链与数据安全国家重点实验室)
;
Zhejiang University(浙江大学)
;
School of Cyber Science and Engineering(网络安全与工程学院)
;
Southeast University(东南大学)
Claw-Eval: Towards Trustworthy Evaluation of Autonomous Agents
Claw-Eval: 向可信的自主代理评估迈进
Bowen Ye, Rang Li, Qibin Yang, Yuanxin Liu, Linli Yao, Hanglong Lv, Zhihui Xie, Chenxin An, Lei Li, Lingpeng Kong, Qi Liu, Zhifang Sui, Tong Yang
机构
*
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University(多媒体信息处理国家重点实验室,计算机学院,北京大学)
;
The University of Hong Kong(香港大学)
GazeMind: A Gaze-Guided LLM Agent for Personalized Cognitive Load Assessment
GazeMind:一种基于注视的LLM代理用于个性化认知负荷评估
Bin Wang, Yue Liu, Benjamin Newman, Ajoy S. Fernandes, Zhiyuan Wang, Robert Cavin, Michele A. Cox, Vijay Rajanna, Takumi Bolte, Melissa Hunfalvay, Ulas Bagci, Michael J. Proulx
机构
*
Gansu Provincial Key Laboratory of Wearable Computing, School of Information Science and Engineering, Lanzhou University(甘肃省可穿戴计算重点实验室,兰州大学信息科学与工程学院)
;
Guangdong-Hong Kong-Macao Joint Laboratory for Emotional Intelligence and Pervasive Computing, Shenzhen MSU-BIT University(粤港澳大湾区情感智能与泛在计算联合实验室,深圳MSU-BIT大学)
;
Department of Computer and Information Engineering, Khalifa University(计算机与信息工程系,哈利法大学)
;
Artificial Intelligence Research Institute, Shenzhen MSU-BIT University(人工智能研究院,深圳MSU-BIT大学)
;
Department of Electrical and Computer Engineering, The University of Hong Kong(电子与计算机工程系,香港大学)
机构
*
Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California(史蒂文斯神经影像与信息学研究所,凯克医学院,南加州大学)
;
Viterbi School of Engineering, University of Southern California(维特比工程学院,南加州大学)
;
Alfred E. Mann Department of Biomedical Engineering, Viterbi School of Engineering, University of Southern California(阿尔弗雷德·E·曼生物医学工程部门,维特比工程学院,南加州大学)
Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors
工具选择:测量LLM代理追求工具性行为的倾向
Jonas Wiedermann-Möller, Leonard Dung, Maksym Andriushchenko
机构
*
Universität Bielefeld(比勒菲尔德大学)
;
Ruhr-Universität Bochum(波鸿鲁尔大学)
;
ELLIS Institute(ELLIS研究所)
;
Max Planck Institute for Intelligent Systems(智能系统马克斯·普朗克研究所)
;
Tübingen AI Center(图宾根人工智能中心)