Luca Nannini, Adam Leon Smith, Michele Joshua Maggini, Enrico Panai, Sandra Feliciano, Aleksandr Tiulkanov, Elena Maran, James Gealy, Piercosma Bisconti
机构
*
Piccadilly Labs(皮卡迪利实验室)
;
Association of AI Ethicists(人工智能伦理学家协会)
;
Centro Singular de Investigación en Tecnoloxías Intelixentes da USC(圣地亚哥德孔波斯特拉大学智能技术卓越研究中心)
;
AIQI Consortium(AIQI联盟)
;
BeEthical
;
INSIGHT – Piaget Research Center for Ecological Human Development(INSIGHT – 皮亚杰生态人类发展研究中心)
;
Responsible Innovations(负责任创新)
;
ForHumanity Europe(ForHumanity欧洲)
;
Alethesis AI
;
SaferAI
;
DEXAI
;
Icaro Lab(伊卡洛斯实验室)
Decocted Experience Improves Test-Time Inference in LLM Agents
解毒经验提升LLM代理的测试时间推理
Maohao Shen, Kaiwen Zha, Zexue He, Zhang-Wei Hong, Siru Ouyang, J. Jon Ryu, Prasanna Sattigeri, Suhas Diggavi, Gregory Wornell
机构
*
Massachusetts Institute of Technology(麻省理工学院)
;
Stanford University(斯坦福大学)
;
MIT-IBM Watson AI Lab(MIT-IBM沃森人工智能实验室)
;
University of Illinois at Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校)
;
University of California, Los Angeles(加利福尼亚大学洛杉矶分校)
CommentsWith an appendix by Marc Chardin. The revised version includes a genus--degree formula for almost complete intersection curves (Corollary C), together with minor improvements to the exposition