mlsanityData to 14 Oct 2026

Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning

arXiv 2503.06034 ↗First posted 8 Mar 2025cs.IR cs.CLcited by 60

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

Abstract (arXiv)

In this paper, we introduce Rank-R1, a novel LLM-based reranker that performs reasoning over both the user query and candidate documents before performing the ranking task. Existing document reranking methods based on large language models (LLMs) typically rely on prompting or fine-tuning LLMs to order or label candidate documents according to their relevance to a query. For Rank-R1, we use a reinforcement learning algorithm along with only a small set of relevance labels (without any reasoning supervision) to enhance the reasoning ability of LLM-based rerankers. Our hypothesis is that adding reasoning capabilities to the rerankers can improve their relevance assessement and ranking capabilities. Our experiments on the TREC DL and BRIGHT datasets show that Rank-R1 is highly effective, especially for complex queries. In particular, we find that Rank-R1 achieves effectiveness on in-domain datasets at par with that of supervised fine-tuning methods, but utilizing only 18% of the training data used by the fine-tuning methods. We also find that the model largely outperforms zero-shot and supervised fine-tuning when applied to out-of-domain datasets featuring complex queries, especially when a 14B-size model is used. Finally, we qualitatively observe that Rank-R1's reasoning process improves the explainability of the ranking results, opening new opportunities for search engine results presentation and fruition.

Key facts. Cited by 60 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 21 of its 43 references that are in the map. First posted on arXiv 8 Mar 2025.

Builds on

21 of 43 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking31 Oct

Other references · 20

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  2. 2024Qwen2.5 Technical Reportcited by 4,942
  3. 2023Zephyr: Direct Distillation of LM Alignmentcited by 506
  4. 2020Document Ranking with a Pretrained Sequence-to-Sequence Modelcited by 376
  5. 2023Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agentscited by 360
  6. 2023Large Language Models are Effective Text Rankers with Pairwise Ranking Promptingcited by 307
  7. 2020Overview of the TREC 2019 deep learning trackcited by 286
  8. 2023Fine-Tuning LLaMA for Multi-Stage Text Retrievalcited by 272
  9. 2021Overview of the TREC 2020 deep learning trackcited by 196
  10. 2022Improving Passage Retrieval with Zero-Shot Question Generationcited by 165
  11. 2024BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrievalcited by 158
  12. 2023RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!cited by 155
8 more
  1. 2023Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labelscited by 86
  2. 2023A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Modelscited by 55
  3. 2024TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategycited by 47
  4. 2023Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Rankingcited by 44
  5. 2024Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankerscited by 43
  6. 2024RankMamba: Benchmarking Mamba's Document Ranking Performance in the Era of Transformerscited by 15
  7. 2024An Investigation of Prompt Variations for Zero-shot LLM-based Rankerscited by 8
  8. 2024MCRanker: Generating Diverse Criteria On-the-Fly to Improve Point-wise LLM Rankerscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 27; 2026: 33.

60 papers.

Sort:

By area:

  1. 2025ReasonIR: Training Retrievers for Reasoning Taskscited by 77
  2. 2026Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interactioncited by 38
  3. 2025DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrievalcited by 37
  4. 2025Rank-K: Test-Time Reasoning for Listwise Rerankingcited by 29
  5. 2025REARANK: Reasoning Re-ranking Agent via Reinforcement Learningcited by 24
  6. 2025Table-R1: Inference-Time Scaling for Table Reasoningcited by 24
  7. 2025MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrievalcited by 21
  8. 2025ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrievalcited by 16
  9. 2025Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learningcited by 14
  10. 2025ThinkQE: Query Expansion via an Evolving Thinking Processcited by 12
  11. 2025ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Rerankingcited by 11
  12. 2025CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoningcited by 11
38 more
  1. 2025Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Searchcited by 11
  2. 2025AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Rerankingcited by 8
  3. 2025Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?cited by 7
  4. 2025Rethinking Reasoning in Document Ranking: Why Chain-of-Thought Falls Shortcited by 7
  5. 2026LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptationcited by 6
  6. 2025SciRerankBench: Benchmarking Rerankers Towards Scientific Retrieval-Augmented Generated LLMscited by 5
  7. 2025TFRank: Think-Free Reasoning Enables Practical Pointwise LLM Rankingcited by 5
  8. 2025Improving Context Fidelity via Native Retrieval-Augmented Reasoningcited by 5
  9. 2025InsertRank: LLMs can reason over BM25 scores to Improve Listwise Rerankingcited by 4
  10. 2026Medical Triage as Pairwise Ranking: A Benchmark for Urgency in Patient Portal Messagescited by 4
  11. 2025RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentationcited by 3
  12. 2025LimRank: Less is More for Reasoning-Intensive Information Rerankingcited by 3
  13. 2026OptiSet: Unified Optimizing Set Selection and Ranking for Retrieval-Augmented Generationcited by 3
  14. 2026MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoningcited by 3
  15. 2026Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Rankingcited by 3
  16. 2025From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrievalcited by 2
  17. 2025Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systemscited by 2
  18. 2026DeepEra: A Deep Evidence Reranking Agent for Scientific Retrieval-Augmented Generated Question Answeringcited by 2
  19. 2026Pailitao-VL: Unified Embedding and Reranker for Real-Time Multi-Modal Industrial Searchcited by 2
  20. 2026Does Reasoning Make Search More Fair? Comparing Fairness in Reasoning and Non-Reasoning Rerankerscited by 2
  21. 2026HeadRank: Decoding-Free Passage Reranking via Preference-Aligned Attention Headscited by 2
  22. 2026ConFit v3: Improving Resume-Job Matching with LLM-based Re-Rankingcited by 2
  23. 2026RL-Index: Reinforcement Learning for Retrieval Index Reasoningcited by 2
  24. 2025R1-Ranker: Teaching LLM Rankers to Reasoncited by 1
  25. 2025Lighting the Way for BRIGHT: Reproducible Baselines with Anserini, Pyserini, and RankLLMcited by 1
  26. 2026SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streamscited by 1
  27. 2026A Survey of Reasoning-Intensive Retrieval: Progress and Challengescited by 1
  28. 2026F-GRPO: Factorized Group-Relative Policy Optimization for Unified Candidate Generation and Rankingcited by 1
  29. 2025How Grounded is Wikipedia? A Study on Structured Evidential Support and Retrievalcited by 0
  30. 2025R3A: Reinforced Reasoning for Relevance Assessment for RAG in User-Generated Content Platformscited by 0
  31. 2026Answer First, Reason Later: Aligning Search Relevance via Mode-Balanced Reinforcement Learningcited by 0
  32. 2026Towards Position-Robust Talent Recommendation via Large Language Modelscited by 0
  33. 2026MARVEL: Multimodal Adaptive Reasoning-intensiVe Expand-rerank and retrievaLcited by 0
  34. 2026HIVE: Query, Hypothesize, Verify An LLM Framework for Multimodal Reasoning-Intensive Retrievalcited by 0
  35. 2026BracketRank: Large Language Model Document Ranking via Reasoning-based Competitive Eliminationcited by 0
  36. 2026Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Rankingcited by 0
  37. 2026Dynamic Infilling Anchors for Format-Constrained Generation in Diffusion Large Language Modelscited by 0
  38. 2026TabRank: Chain-of-Thought Distillation for Table Re-Rankerscited by 0

50 most cited of 60 All 60 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking
  2. 2025ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Reranking
  3. 2026Optimizing RAG Rerankers with LLM Feedback via Reinforcement Learning
  4. 2025DeAR: Dual-Stage Document Reranking with Reasoning Agents via LLM Distillation
  5. 2025ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability
  6. 2025DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation
  7. 2025Rank1: Test-Time Compute for Reranking in Information Retrieval
  8. 2026Tool-Adaptive LLM Reranker