一作NeurIPS 2026Poster
Rationale-Guided Policy Optimization: Learning to Reason with Adaptive Rationale Scaffolding
Hoang Phan · Minh Pham · Chau Pham · Chinmay Hegde · Trung Le · Qi Lei
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。
Hoang Phan · Minh Pham · Chau Pham · Chinmay Hegde · Trung Le · Qi Lei
Quyen Tran · Hai Nguyen · Quan Dao · Hoang Phan · Linh Van · Khoat Than · Dinh Q. Phung · Dimitris Metaxas · Trung Le
Hoang Phan · Xianjun Yang · Yuanshun Yao · Jingyu Zhang · Shengjie Bi · Xiaocheng Tang · Madian Khabsa · Lijuan Liu · Deren Lei
Reinforcement learning with verifiable rewards (RLVR) has delivered impressive gains in mathematical and multimodal reasoning and has become a standard post-training paradigm for contemporary language and vision-language models. However, the RLVR recipe introduces a significant risk of capability...