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

arXiv: https://arxiv.org/abs/2503.06034 · HTML: https://mlsanity.com/paper/2503.06034/

## 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.

## Placed in

- LLM reasoning / [Knowledge- and tool-augmented reasoning](https://mlsanity.com/lr/knowledge-and-tool-augmented-reasoning/)

## Builds on (most cited first, 21 of 21)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Zephyr: Direct Distillation of LM Alignment](https://mlsanity.com/paper/2310.16944/) (2023)
- [Document Ranking with a Pretrained Sequence-to-Sequence Model](https://mlsanity.com/paper/2003.06713/) (2020)
- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting](https://mlsanity.com/paper/2306.17563/) (2023)
- [Overview of the TREC 2019 deep learning track](https://mlsanity.com/paper/2003.07820/) (2020)
- [Fine-Tuning LLaMA for Multi-Stage Text Retrieval](https://mlsanity.com/paper/2310.08319/) (2023)
- [Overview of the TREC 2020 deep learning track](https://mlsanity.com/paper/2102.07662/) (2021)
- [Improving Passage Retrieval with Zero-Shot Question Generation](https://mlsanity.com/paper/2204.07496/) (2022)
- [BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2407.12883/) (2024)
- [RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!](https://mlsanity.com/paper/2312.02724/) (2023)
- [Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labels](https://mlsanity.com/paper/2310.14122/) (2023)
- [A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models](https://mlsanity.com/paper/2310.09497/) (2023)
- [TourRank: Utilizing Large Language Models for Documents Ranking with a Tournament-Inspired Strategy](https://mlsanity.com/paper/2406.11678/) (2024)
- [Open-source Large Language Models are Strong Zero-shot Query Likelihood Models for Document Ranking](https://mlsanity.com/paper/2310.13243/) (2023)
- [Attention in Large Language Models Yields Efficient Zero-Shot Re-Rankers](https://mlsanity.com/paper/2410.02642/) (2024)
- [JudgeRank: Leveraging Large Language Models for Reasoning-Intensive Reranking](https://mlsanity.com/paper/2411.00142/) (2024)
- [RankMamba: Benchmarking Mamba's Document Ranking Performance in the Era of Transformers](https://mlsanity.com/paper/2403.18276/) (2024)
- [An Investigation of Prompt Variations for Zero-shot LLM-based Rankers](https://mlsanity.com/paper/2406.14117/) (2024)
- [MCRanker: Generating Diverse Criteria On-the-Fly to Improve Point-wise LLM Rankers](https://mlsanity.com/paper/2404.11960/) (2024)

## Built on by (most cited first, 30 of 60)

- [ReasonIR: Training Retrievers for Reasoning Tasks](https://mlsanity.com/paper/2504.20595/) (2025)
- [Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interaction](https://mlsanity.com/paper/2605.05242/) (2026)
- [DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval](https://mlsanity.com/paper/2508.07995/) (2025)
- [Rank-K: Test-Time Reasoning for Listwise Reranking](https://mlsanity.com/paper/2505.14432/) (2025)
- [REARANK: Reasoning Re-ranking Agent via Reinforcement Learning](https://mlsanity.com/paper/2505.20046/) (2025)
- [Table-R1: Inference-Time Scaling for Table Reasoning](https://mlsanity.com/paper/2505.23621/) (2025)
- [MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval](https://mlsanity.com/paper/2506.12364/) (2025)
- [ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval](https://mlsanity.com/paper/2510.08252/) (2025)
- [Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learning](https://mlsanity.com/paper/2505.24105/) (2025)
- [ThinkQE: Query Expansion via an Evolving Thinking Process](https://mlsanity.com/paper/2506.09260/) (2025)
- [ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking](https://mlsanity.com/paper/2506.03487/) (2025)
- [CLaRa: Bridging Retrieval and Generation with Continuous Latent Reasoning](https://mlsanity.com/paper/2511.18659/) (2025)
- [Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Search](https://mlsanity.com/paper/2512.00968/) (2025)
- [AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking](https://mlsanity.com/paper/2505.18512/) (2025)
- [Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?](https://mlsanity.com/paper/2505.16886/) (2025)
- [Rethinking Reasoning in Document Ranking: Why Chain-of-Thought Falls Short](https://mlsanity.com/paper/2510.08985/) (2025)
- [LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptation](https://mlsanity.com/paper/2601.05192/) (2026)
- [SciRerankBench: Benchmarking Rerankers Towards Scientific Retrieval-Augmented Generated LLMs](https://mlsanity.com/paper/2508.08742/) (2025)
- [TFRank: Think-Free Reasoning Enables Practical Pointwise LLM Ranking](https://mlsanity.com/paper/2508.09539/) (2025)
- [Improving Context Fidelity via Native Retrieval-Augmented Reasoning](https://mlsanity.com/paper/2509.13683/) (2025)
- [InsertRank: LLMs can reason over BM25 scores to Improve Listwise Reranking](https://mlsanity.com/paper/2506.14086/) (2025)
- [Medical Triage as Pairwise Ranking: A Benchmark for Urgency in Patient Portal Messages](https://mlsanity.com/paper/2601.13178/) (2026)
- [RAG in the Wild: On the (In)effectiveness of LLMs with Mixture-of-Knowledge Retrieval Augmentation](https://mlsanity.com/paper/2507.20059/) (2025)
- [LimRank: Less is More for Reasoning-Intensive Information Reranking](https://mlsanity.com/paper/2510.23544/) (2025)
- [OptiSet: Unified Optimizing Set Selection and Ranking for Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.05027/) (2026)
- [MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoning](https://mlsanity.com/paper/2603.03379/) (2026)
- [Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Ranking](https://mlsanity.com/paper/2607.19747/) (2026)
- [From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval](https://mlsanity.com/paper/2505.23059/) (2025)
- [Mitigating Hallucination in Large Language Models (LLMs): An Application-Oriented Survey on RAG, Reasoning, and Agentic Systems](https://mlsanity.com/paper/2510.24476/) (2025)
- [DeepEra: A Deep Evidence Reranking Agent for Scientific Retrieval-Augmented Generated Question Answering](https://mlsanity.com/paper/2601.16478/) (2026)

## 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.