机构
*
University of Michigan(密歇根大学)
;
New York University(纽约大学)
;
University of Wisconsin-Madison(威斯康星大学麦迪逊分校)
;
Algoverse AI
;
University of Aberdeen(阿伯丁大学)
;
University of Oxford(牛津大学)
Comments12 pages, 1 figure, 3 tables. Accepted at PAKDD 2026
Journal refIn: Wong, R.CW., et al. Advances in Knowledge Discovery and Data Mining. PAKDD 2026. Lecture Notes in Computer Science(), vol 16600. Springer, Singapore
机构
*
Program in Computational Biology & Biomedical Informatics, Yale University(计算生物学与生物医学信息学项目,耶鲁大学)
;
Department of Biomedical Informatics & Data Science, Yale University(生物医学信息学与数据科学系,耶鲁大学)
;
Department of Computer Science, Yale University(计算机科学系,耶鲁大学)
;
Department of Biosystems Science and Engineering, ETH Zurich(生物系统科学与工程系,苏黎世联邦理工学院)
;
Department of Computer Science, Stanford University(计算机科学系,斯坦福大学)
;
Department of Bioinformatics, UT Southwestern Medical Center(生物信息学系,德克萨斯西南医学中心)
Compositional Reasoning Depth Predicts Clinical AI Failure: Empirical Evidence Consistent with Transformer Compositionality Limits in Electronic Health Record Question Answering
组合推理深度预测临床AI失败:与电子健康记录问答中Transformer组合性限制一致的实证证据
Sanjay Basu
机构
*
University of California San Francisco(加州大学旧金山分校)
;
Waymark
机构
*
HCCL, The Chinese University of Hong Kong, Hong Kong, China(香港中文大学人工智能研究中心,香港,中国)
;
University of Cambridge, Cambridge, United Kingdom(剑桥大学,剑桥,英国)
;
MMLab, The Chinese University of Hong Kong, Hong Kong, China(香港中文大学人工智能实验室,香港,中国)
;
Shanghai Artificial Intelligence Laboratory, Shanghai, China(上海人工智能实验室,上海,中国)
R-APS: Compositional Reasoning and In-Context Meta-Learning for Constrained Design via Reflective Adversarial Pareto Search
R-APS:基于反思性对抗帕累托搜索的组合推理与上下文元学习用于约束设计
João Pedro Gandarela, Thiago Rios, Stefan Menzel, André Freitas
机构
*
Idiap Research Institute(Idiap研究 institute)
;
École Polytechnique Fédérale de Lausanne(瑞士联邦理工学院)
;
Honda Research Institute Europe(本田欧洲研究机构)
;
Department of Computer Science, University of Manchester(曼彻斯特大学计算机科学系)
;
National Biomarker Centre, CRUK-MI, University of Manchester(曼彻斯特大学国家生物标志物中心)
SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning
SafeMCP:基于环境接地前瞻推理的LLM智能体防御主动功率调节
Lichao Wang, Zhaoxing Ren, Tianzhuo Yang, Jiaming Ji, Chi Harold Liu, Yaodong Yang, Juntao Dai
机构
*
Beijing Institute of Technology(北京理工大学)
;
Beijing Academy of Artificial Intelligence(北京人工智能研究院)
;
Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院)