作者位次 #4/9ICLR 2026Poster· Reinforcement Learning / Planning
LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision
Jundong Xu · Hao (Scofield) Fei · Huichi Zhou · Xin Quan · Qijun Huang · Shengqiong Wu · William Wang · Mong-Li Lee · Wynne Hsu