From Passive Observer to Active Critic: Reinforcement Learning Elicits Process Reasoning for Robotic Manipulation

作者：Yibin Liu, Yaxing Lyu, Daqi Gao, Zhixuan Liang, Weiliang Tang, Shilong Mu, Xiaokang Yang, Yao Mu · 单位：Shanghai Jiao Tong University, Northeastern University, Xiamen University Malaysia, The University of Hong Kong, The Chinese University of Hong Kong · 会议/期刊：arXiv · 日期：2026-03-16 · 来源：High-Level Structured Planning / Multimodal Reasoning / Common Reasoning