A Survey of Reasoning-Intensive Retrieval: Progress and Challenges

TL;DR

This survey reviews recent progress in Reasoning-Intensive Retrieval, categorizing benchmarks and methods, and discusses challenges and future directions in integrating reasoning into retrieval systems.

Contribution

It provides a systematic framework and taxonomy for organizing current RIR efforts, addressing fragmentation and guiding future research.

Findings

Systematized RIR benchmarks by knowledge domains and modalities.

Developed a taxonomy categorizing reasoning integration methods.

Outlined key challenges and future research directions.

Abstract

Reasoning-Intensive Retrieval (RIR) targets retrieval settings where relevance is mediated by latent inferential links between a query and supporting 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. To provide a clear roadmap for this rapidly growing yet fragmented area, this survey (1) systematizes existing RIR benchmarks by knowledge domains and modalities, providing a detailed analysis of the current landscape; (2) introduces a structured taxonomy that categorizes methods based on where and how reasoning is integrated into the retrieval pipeline, alongside an analysis of their trade-offs and practical applications; and (3) summarizes challenges and future directions to guide research in this evolving field.