TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents
Leitian Tao, Baolin Peng, Wenlin Yao, Tao Ge, Hao Cheng, Hang Wang, Jianfeng Gao, Sharon Li
July 2026
arXiv | July 2026
Leitian Tao, Baolin Peng, Wenlin Yao, Tao Ge, Hao Cheng, Hang Wang, Jianfeng Gao, Sharon Li
July 2026
arXiv | July 2026
Leitian Tao, Baolin Peng, Wenlin Yao, Tao Ge, Hao Cheng, Hang Wang, Jianfeng Gao, Sharon Li
July 2026
arXiv | July 2026
Leitian Tao, Baolin Peng, Wenlin Yao, Tao Ge, Hao Cheng, Hang Wang, Jianfeng Gao, Sharon Li
July 2026
arXiv | July 2026