作者位次 #5/8ICML 2026Poster· Reinforcement Learning / Batch/Offline
RAD: Retrieval High-quality Demonstrations to Enhance Decision-making
Lu Guo · Yixiang Shan · Zhengbang Zhu · Qifan Liang · Lichang Song · Ting Long · Weinan Zhang · Yi Chang
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。
Lu Guo · Yixiang Shan · Zhengbang Zhu · Qifan Liang · Lichang Song · Ting Long · Weinan Zhang · Yi Chang
Lichang Song · Ting Long · Yi Chang
Retrieval-Augmented Generation (RAG) has demonstrated strong effectiveness in knowledge-intensive tasks by grounding language generation in external evidence. Despite its success, many existing RAG systems are built based on a ranking-centric, asymmetric dependency paradigm, where the generation...