作者位次 #2/7ICLR 2026Poster· Reinforcement Learning / Everything Else
Agentic Reinforcement Learning with Implicit Step Rewards
Xiaoqian Liu · Ke Wang · Yuchuan Wu · Fei Huang · Yongbin Li · Jianbin Jiao · Junge Zhang
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。
Xiaoqian Liu · Ke Wang · Yuchuan Wu · Fei Huang · Yongbin Li · Jianbin Jiao · Junge Zhang
Chonghua Liao · Ke Wang · Yuchuan Wu · Ruoran Li · Fei Huang · Yongbin Li
Role-playing agents (RPAs) require balancing multiple objectives, such as instruction following, persona consistency, and stylistic fidelity, which are not always perfectly aligned across different dimensions. While prior work has primarily relied on supervised fine-tuning or reinforcement learni...