Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following
Kongcheng Zhang · QI YAO · Shunyu Liu · Wenjian Zhang · Min Cen · Yang Zhou · Wenkai Fang · Yiru Zhao · Baisheng Lai · Mingli Song
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。
Kongcheng Zhang · QI YAO · Shunyu Liu · Wenjian Zhang · Min Cen · Yang Zhou · Wenkai Fang · Yiru Zhao · Baisheng Lai · Mingli Song
Yang Zhou · Sunzhu Li · Shunyu Liu · Wenkai Fang · Kongcheng Zhang · Jiale Zhao · Jingwen Yang · Yihe Zhou · Jianwei Lv · Tongya Zheng · Hengtong Lu · Chen Wei · Xie Yan · Mingli Song
Sunzhu Li · Jiale Zhao · Huimin Ren · Zhenlin Wei · Yang Zhou · Jingwen Yang · Shunyu Liu · Kaike Zhang · Chen Wei
Reinforcement Learning with Verifiable Rewards (RLVR) has driven substantial progress in reasoning-intensive domains like mathematics. However, optimizing open-ended generation remains challenging due to the lack of ground truth. While rubric-based evaluation offers a structured proxy for verific...