Start Classifying: Categorical Critics for LLM Reinforcement Learning

Conference on Language Modeling (COLM), 2026

Zhijian Zhou#, Long Li#, Xuan Zhang, Zongkai Liu, Yulei Qin, Ke Li, Xing Sun, Xiaoyu Tan*, Chao Qu*†, Yuan Qi*

# Equal contribution    * Corresponding author; Project lead

[PDF]    [Code]