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。
Qikai Chang · Zhenrong Zhang · Pengfei Hu · Jun Du · Jiefeng Ma · Yicheng Pan · Jianshu Zhang · Quan Liu · Gao Jianqing
Fei Wu · Zhenrong Zhang · Qikai Chang · Jianshu Zhang · Quan Liu · Jun Du
Reinforcement Learning with Verifiable Rewards (RLVR) elicits long chain-of-thought reasoning in large language models (LLMs), but outcome-based rewards lead to coarse-grained advantage estimation. While existing approaches improve RLVR via token-level entropy or sequence-level length control, th...