一作ICLR 2026Poster· Applications / Language, Speech and Dialog
R4: Nested Reasoning-Retrieval for Reward Modeling in Role-Playing Agents
Renzhi Wang · Chongqiang Wei · Zhisheng Wang · Piji Li
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。
Renzhi Wang · Chongqiang Wei · Zhisheng Wang · Piji Li
Yixin Bu · Guanyun Zou · Renzhi Wang · Runze Xia · Cunjun Wang · Hongliang Dai · Xiaoqing Ma · Piji Li