作者位次 #5/11NeurIPS 2026Poster
The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning
Jing Liang · Hongyao Tang · Yi Ma · Yancheng He · Weixun Wang · Xiaoyang Li · Wenbo Su · Jinyi Liu · YAN ZHENG · Jianye Hao · Bo Zheng