# ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability

arXiv: https://arxiv.org/abs/2508.07050 · HTML: https://mlsanity.com/paper/2508.07050/

## Key facts

- Cited by 42 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 7 of its 50 references that are in the map.
- First posted on arXiv 9 Aug 2025.

## Placed in

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

## Builds on (most cited first, 7 of 7)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Large Language Models for Information Retrieval: A Survey](https://mlsanity.com/paper/2308.07107/) (2023)
- [Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting](https://mlsanity.com/paper/2306.17563/) (2023)
- [Agentic Reinforced Policy Optimization](https://mlsanity.com/paper/2507.19849/) (2025)
- [Holistic Evaluation of Language Models](https://mlsanity.com/paper/2211.09110/) (2022)
- [RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Models](https://mlsanity.com/paper/2309.15088/) (2023)
- [CoRanking: Collaborative Ranking with Small and Large Ranking Agents](https://mlsanity.com/paper/2503.23427/) (2025)

## Built on by (most cited first, 30 of 42)

- [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)
- [ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval](https://mlsanity.com/paper/2510.08252/) (2025)
- [Agentic-R: Learning to Retrieve for Agentic Search](https://mlsanity.com/paper/2601.11888/) (2026)
- [LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval](https://mlsanity.com/paper/2603.01425/) (2026)
- [Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrieval](https://mlsanity.com/paper/2509.24869/) (2025)
- [MR2-Bench: Going Beyond Matching to Reasoning in Multimodal Retrieval](https://mlsanity.com/paper/2509.26378/) (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)
- [Query-focused and Memory-aware Reranker for Long Context Processing](https://mlsanity.com/paper/2602.12192/) (2026)
- [TFRank: Think-Free Reasoning Enables Practical Pointwise LLM Ranking](https://mlsanity.com/paper/2508.09539/) (2025)
- [Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Models](https://mlsanity.com/paper/2511.07581/) (2025)
- [ELVA: Exploring Ranking-Driven Universal Multimodal Retrieval](https://mlsanity.com/paper/2606.20280/) (2026)
- [Reason to Retrieve: Enhancing Query Understanding through Decomposition and Interpretation](https://mlsanity.com/paper/2509.06544/) (2025)
- [LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrieval](https://mlsanity.com/paper/2510.13217/) (2025)
- [E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Search](https://mlsanity.com/paper/2510.22733/) (2025)
- [Think When Needed: Model-Aware Reasoning Routing for LLM-based Ranking](https://mlsanity.com/paper/2601.18146/) (2026)
- [LimRank: Less is More for Reasoning-Intensive Information Reranking](https://mlsanity.com/paper/2510.23544/) (2025)
- [GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs](https://mlsanity.com/paper/2511.11653/) (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)
- [Does Reasoning Make Search More Fair? Comparing Fairness in Reasoning and Non-Reasoning Rerankers](https://mlsanity.com/paper/2603.10332/) (2026)
- [Very Efficient Listwise Multimodal Reranking for Long Documents](https://mlsanity.com/paper/2605.11864/) (2026)
- [Training Documents Reranker with Search Rubrics for Deep Research Agent](https://mlsanity.com/paper/2608.03527/) (2026)
- [Lighting the Way for BRIGHT: Reproducible Baselines with Anserini, Pyserini, and RankLLM](https://mlsanity.com/paper/2509.02558/) (2025)
- [RANKVIDEO: Reasoning Reranking for Text-to-Video Retrieval](https://mlsanity.com/paper/2602.02444/) (2026)
- [A Survey of Reasoning-Intensive Retrieval: Progress and Challenges](https://mlsanity.com/paper/2605.00063/) (2026)
- [AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Research](https://mlsanity.com/paper/2609.32472/) (2026)
- [Re-Rankers as Relevance Judges](https://mlsanity.com/paper/2601.04455/) (2026)

## Abstract (arXiv)

Large Language Model (LLM) based listwise ranking has shown superior performance in many passage ranking tasks. With the development of Large Reasoning Models (LRMs), many studies have demonstrated that step-by-step reasoning during test-time helps improve listwise ranking performance. However, due to the scarcity of reasoning-intensive training data, existing rerankers perform poorly in many complex ranking scenarios, and the ranking ability of reasoning-intensive rerankers remains largely underdeveloped. In this paper, we first propose an automated reasoning-intensive training data synthesis framework, which sources training queries and passages from diverse domains and applies DeepSeek-R1 to generate high-quality training labels. To empower the listwise reranker with strong reasoning ability, we further propose a two-stage training approach, which includes a cold-start supervised fine-tuning (SFT) stage and a reinforcement learning (RL) stage. During the RL stage, we design a novel multi-view ranking reward tailored to the multi-turn nature of listwise ranking. Extensive experiments demonstrate that our trained reasoning-intensive reranker ReasonRank outperforms existing baselines significantly and also achieves much lower latency than the pointwise reranker. Our codes are available at https://github.com/8421BCD/ReasonRank.