A Survey of Reasoning-Intensive Retrieval: Progress and Challenges

ArXi:2605.00063v1 Announce Type: cross Reasoning-Intensive Retrieval (RIR) targets retrieval settings where relevance is mediated by latent inferential links between a query and ing evidence, rather than semantic similarity. Motivated by the emergent reasoning abilities of Large Language Models (LLMs), recent work integrates these capabilities into the IR field, spanning the entire pipeline from benchmarks to retrievers and rerankers. Despite this progress, the field lacks a systematic framework to organize current efforts and articulate a clear path forward.