Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It
为什么多步工具使用强化学习会崩溃以及监督信号如何修复它
Yupu Hao, Zhuoran Jin, Huanxuan Liao, Kang Liu, Jun Zhao
机构
*
The Key Laboratory of Cognition and Decision Intelligence for Complex Systems, Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所复杂系统认知与决策智能重点实验室)
;
School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院)
CommentsNASA-DARES 2025 white paper, 5 pages, 3 figures. Originally submitted in 2025 under topic 8 (Prepare for the Discovery of Life Beyond Earth and Subsequent Post-Discovery Activities), which now falls under focus area 9 (Astrobiology in Society)
Plausible but Wrong: A case study on Agentic Failures in Astrophysical Workflows
可能但错误:天体物理工作流中代理失败的案例研究
Shivam Rawat, Lucie Flek
机构
*
Bonn-Aachen International Center for Information Technology, University of Bonn, Germany(波恩-阿森国际信息科技中心,波恩大学,德国)
;
Lamarr Institute for Machine Learning and Artificial Intelligence, Germany(拉马尔机器学习与人工智能研究所,德国)
ASSCG: Just-Right Gating over Chattering for Fast-Slow LLM Planning in Autonomous Driving
ASSCG:自动驾驶中快慢LLM规划的恰到好处门控
Sining Ang, Yuan Chen, Liu Haiyan, Xuanyao Mao, Jason Bao, Xuliang, Bingchuan Sun, Yan Wang
机构
*
Institute for AI Industry Research (AIR), Tsinghua University(清华大学人工智能产业研究院)
;
Department of Automation, University of Science and Technology of China(中国科学技术大学自动化系)
;
Beijing University of Aeronautics and Astronautics(北京航空航天大学)
;
Lenovo Group Limited(联想集团)
机构
*
University of Chicago(芝加哥大学)
;
The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))
;
Stanford University(斯坦福大学)
;
University of Science and Technology of China(中国科学技术大学)
;
Meituan(美团)
NeuXtalViz: Interactive Three-Dimensional Visualization and Analysis for Single-Crystal Neutron Diffraction
NeuXtalViz:单晶中子衍射的交互式三维可视化与分析
Zachary Morgan, Zhongcan Xiao, Sylwia Pawledzio, Iris Ye, Kathleen Loughlin, Shiyun Jin, Vickie Lynch, Thomas Proffen, Christina Hoffmann, Xiaoping Wang