作者位次 #6/8ICLR 2026Poster· Reinforcement Learning / Deep RL
Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents
Guoqing Wang · Sunhao Dai · Guangze Ye · Zeyu Gan · Wei Yao · Yong Deng · Xiaofeng Wu · zhenzhe ying