作者位次 #2/5ICLR 2026Poster· Reinforcement Learning / Deep RL
Native Reasoning Models: Training Language Models to Reason on Unverifiable Data
Yuanfu Wang · Zhixuan Liu · Xiangtian Li · Chaochao Lu · yang chao
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。
Yuanfu Wang · Zhixuan Liu · Xiangtian Li · Chaochao Lu · yang chao
Shuyang Zhang · Zhixuan Liu · Zhichen Dong · Hao Zhang · Chaochao Lu · Chao Yang
Prompt optimizers are widely used to create high-quality prompts for Large Language Models (LLMs), but their effectiveness remains unstable in practice. This instability is caused by the misalignment between conservative needs (e.g., safety compliance) and open-ended goals (e.g., creative writing...