作者位次 #7/9ICML 2026Spotlight· Reinforcement Learning / Batch/Offline
Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning
Baolong Bi · Shenghua Liu · Yiwei Wang · Siqian Tong · Lingrui Mei · Yuyao Ge · Yilong Xu · Jiafeng Guo · Xueqi Cheng