作者位次 #8/8ICML 2026Poster· Reinforcement Learning / Multi-agent
EAPO: Enhancing Policy Optimization with On-Demand Expert Assistance
Siyao Song · Cong Ma · Zhihao Cheng · Shiye Lei · MINGHAO LI · Ying Zeng · Huaixiao Tou · Kai Jia
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。
Siyao Song · Cong Ma · Zhihao Cheng · Shiye Lei · MINGHAO LI · Ying Zeng · Huaixiao Tou · Kai Jia
Zhuocheng Yu · Feng Zhang · Sujian Li · Kai Jia
Zirun Guo · Minjie Hong · Feng Zhang · Kai Jia · Tao Jin
Zheng Li · Qingxiu Dong · Jingyuan Ma · Di Zhang · Kai Jia · Zhifang Sui
Recently, large reasoning models demonstrate exceptional performance on various tasks. However, reasoning models always consume excessive tokens even for simple queries, leading to resource waste and prolonged user latency. To address this challenge, we propose SelfBudgeter - a self-adaptive reas...