一作ICLR 2026Poster· Applications / Language, Speech and Dialog
DeepRAG: Thinking to Retrieve Step by Step for Large Language Models
Xinyan Guan · Jiali Zeng · Fandong Meng · Chunlei Xin · Yaojie Lu · Hongyu Lin · Xianpei Han · Le Sun · Jie Zhou
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。
Xinyan Guan · Jiali Zeng · Fandong Meng · Chunlei Xin · Yaojie Lu · Hongyu Lin · Xianpei Han · Le Sun · Jie Zhou
Xinyan Guan · Jiali Zeng · Chunlei Xin · Yaojie Lu · Hongyu Lin · Xianpei Han · Le Sun · Fandong Meng
Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks, creating safety risks where plausible-sounding but incorrect derivations mislead users. We characterize this futile reasoning phenomenon through systematic analysis, revealing univ...
Yingzhi Mao · Chunkang Zhang · Junxiang Wang · Xinyan Guan · Boxi Cao · Yaojie Lu · Hongyu Lin · Xianpei Han · Le Sun
Large Reasoning Models (LRMs) achieve strong performance on complex multi-step reasoning, yet they still exhibit severe safety failures such as harmful content generation. Existing methods often apply coarse-grained constraints over the entire reasoning trajectories, which can undermine reasoning...