作者位次 #4/8NeurIPS 2026Poster
STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning
Junjie Zhang · Guozheng Ma · Shunyu Liu · Zetian Hu · Yongcheng Jing · Ting-En Lin · Yongbin Li · Dacheng Tao
首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Junjie Zhang · Guozheng Ma · Shunyu Liu · Zetian Hu · Yongcheng Jing · Ting-En Lin · Yongbin Li · Dacheng Tao
Zetian Hu · Shunyu Liu · Ting-En Lin · Fei Huang · Yongbin Li · Dacheng Tao
Recent work has aimed to enhance the reasoning capabilities of language models, but these methods are often limited to domains with objectively verifiable answers. To overcome this limitation, we introduce Reasoning-Guided Exploration for Online DPO (RGE-DPO), a novel self-play framework designed...