Authors: Zhuofeng Li , Haoxiang Zhang , Cong Wei , Pan Lu , Ping Nie , Yi Lu , Yuyang Bai , Shangbin Feng , Hangxiao Zhu , Ming Zhong , Yuyu Zhang , Jianwen Xie , Yejin Choi , James Zou , Jiawei Han , Wenhu Chen , Jimmy Lin , Dongfu Jiang , Yu Zhang View PDF Abstract: Modern retrieval systems, whether lexical or semantic, expose a corpus through a fixed similarity interface that compresses access into a single top-k retrieval step before reasoning. This abstraction is efficient, but for agentic search, it becomes a bottleneck: exact lexical constraints, sparse clue conjunctions, local context checks, and multi-step hypothesis refinement are difficult to implement by calling a conventional off-the-shelf retriever, and evidence filtered out early cannot be recovered by stronger downstream reasoning.…