mlsanityData to 14 Oct 2026

A Survey of Reasoning-Intensive Retrieval: Progress and Challenges

arXiv 2605.00063 ↗First posted 30 Apr 2026cs.IR cs.AIcited by 1

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

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.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 32 of its 100 references that are in the map. First posted on arXiv 30 Apr 2026.

Builds on

32 of 100 references.

Closest ancestors · 19

Same direction, newest first

  1. 2025GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs10 Nov
  2. 2025Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Models10 Nov
  3. 2025Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigm16 Oct
  4. 2025LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrieval15 Oct
  5. 2025Refine Thought: A Test-Time Inference Method for Embedding Model Reasoning14 Oct
  6. 2025Your Dense Retriever is Secretly an Expeditious Reasoner27 Sep
  7. 2025Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval8 Sep
  8. 2025Reason to Retrieve: Enhancing Query Understanding through Decomposition and Interpretation8 Sep
  9. 2025TFRank: Think-Free Reasoning Enables Practical Pointwise LLM Ranking13 Aug
  10. 2025DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval11 Aug
  11. 2025ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability9 Aug
  12. 2025InsertRank: LLMs can reason over BM25 scores to Improve Listwise Reranking17 Jun
7 more
  1. 2025Rank-K: Test-Time Reasoning for Listwise Reranking20 May
  2. 2025ReasonIR: Training Retrievers for Reasoning Tasks29 Apr
  3. 2025Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning8 Mar
  4. 2025Rank1: Test-Time Compute for Reranking in Information Retrieval25 Feb
  5. 2025O1 Embedder: Let Retrievers Think Before Action11 Feb
  6. 2024JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking31 Oct
  7. 2024RAR-b: Reasoning as Retrieval Benchmark9 Apr

Other references · 13

  1. 2024Gecko: Versatile Text Embeddings Distilled from Large Language Modelscited by 83
  2. 2025UME-R1: Exploring Reasoning-Driven Generative Multimodal Embeddingscited by 38
  3. 2025R2MED: A Benchmark for Reasoning-Driven Medical Retrievalcited by 22
  4. 2025ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrievalcited by 16
  5. 2025EnrichIndex: Using LLMs to Enrich Retrieval Indices Offlinecited by 15
  6. 2026AgentIR: Reasoning-Aware Retrieval for Deep Research Agentscited by 13
  7. 2025BESPOKE: Benchmark for Search-Augmented Large Language Model Personalization via Diagnostic Feedbackcited by 7
  8. 2025MR2-Bench: Going Beyond Matching to Reasoning in Multimodal Retrievalcited by 7
  9. 2025CoQuIR: A Comprehensive Benchmark for Code Quality-Aware Information Retrievalcited by 6
  10. 2025ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Rerankingcited by 6
  11. 2025Imagine All The Relevance: Scenario-Profiled Indexing with Knowledge Expansion for Dense Retrievalcited by 5
  12. 2025BRIGHT+: Upgrading the BRIGHT Benchmark with MARCUS, a Multi-Agent RAG Clean-Up Suitecited by 2
1 more
  1. 2025A Representation Sharpening Framework for Zero Shot Dense Retrievalcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Beyond Polarization: The Generative Constraint of Chain-of-Thought in Pointwise Rerankingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models
  2. 2026Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems
  3. 2025RaDeR: Reasoning-aware Dense Retrieval Models
  4. 2025Reasoning in Action: MCTS-Driven Knowledge Retrieval for Large Language Models
  5. 2025Lighting the Way for BRIGHT: Reproducible Baselines with Anserini, Pyserini, and RankLLM
  6. 2025DeepRAG: Thinking to Retrieve Step by Step for Large Language Models
  7. 2025FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs
  8. 2025TongSearch-QR: Reinforced Query Reasoning for Retrieval