mlsanityData to 14 Oct 2026

ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability

arXiv 2508.07050 ↗First posted 9 Aug 2025cs.IR cs.AI cs.CLcited by 42

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

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.

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.

Builds on

7 of 50 references.

References · 7

  1. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  2. 2023Large Language Models for Information Retrieval: A Surveycited by 331
  3. 2023Large Language Models are Effective Text Rankers with Pairwise Ranking Promptingcited by 307
  4. 2025Agentic Reinforced Policy Optimizationcited by 172
  5. 2022Holistic Evaluation of Language Modelscited by 131
  6. 2023RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Modelscited by 70
  7. 2025CoRanking: Collaborative Ranking with Small and Large Ranking Agentscited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 13; 2026: 29.

42 papers.

Sort:

By area:

  1. 2026Beyond Semantic Similarity: Rethinking Retrieval for Agentic Search via Direct Corpus Interactioncited by 38
  2. 2025DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrievalcited by 37
  3. 2025ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrievalcited by 16
  4. 2026Agentic-R: Learning to Retrieve for Agentic Searchcited by 11
  5. 2026LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrievalcited by 9
  6. 2025Retro*: Optimizing LLMs for Reasoning-Intensive Document Retrievalcited by 7
  7. 2025MR2-Bench: Going Beyond Matching to Reasoning in Multimodal Retrievalcited by 7
  8. 2025Rethinking Reasoning in Document Ranking: Why Chain-of-Thought Falls Shortcited by 7
  9. 2026LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptationcited by 6
  10. 2026Query-focused and Memory-aware Reranker for Long Context Processingcited by 6
  11. 2025TFRank: Think-Free Reasoning Enables Practical Pointwise LLM Rankingcited by 5
  12. 2025Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Modelscited by 5
30 more
  1. 2026ELVA: Exploring Ranking-Driven Universal Multimodal Retrievalcited by 5
  2. 2025Reason to Retrieve: Enhancing Query Understanding through Decomposition and Interpretationcited by 4
  3. 2025LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrievalcited by 4
  4. 2025E2Rank: Unifying Text Embedding and Listwise Reranking for Effective and Efficient Searchcited by 4
  5. 2026Think When Needed: Model-Aware Reasoning Routing for LLM-based Rankingcited by 4
  6. 2025LimRank: Less is More for Reasoning-Intensive Information Rerankingcited by 3
  7. 2025GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMscited by 3
  8. 2026OptiSet: Unified Optimizing Set Selection and Ranking for Retrieval-Augmented Generationcited by 3
  9. 2026MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoningcited by 3
  10. 2026Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Rankingcited by 3
  11. 2026Does Reasoning Make Search More Fair? Comparing Fairness in Reasoning and Non-Reasoning Rerankerscited by 2
  12. 2026Very Efficient Listwise Multimodal Reranking for Long Documentscited by 2
  13. 2026Training Documents Reranker with Search Rubrics for Deep Research Agentcited by 2
  14. 2025Lighting the Way for BRIGHT: Reproducible Baselines with Anserini, Pyserini, and RankLLMcited by 1
  15. 2026RANKVIDEO: Reasoning Reranking for Text-to-Video Retrievalcited by 1
  16. 2026A Survey of Reasoning-Intensive Retrieval: Progress and Challengescited by 1
  17. 2026AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Researchcited by 1
  18. 2026Re-Rankers as Relevance Judgescited by 0
  19. 2026CRE-T1 Preview Technical Report: Beyond Contrastive Learning for Reasoning-Intensive Retrievalcited by 0
  20. 2026Towards Position-Robust Talent Recommendation via Large Language Modelscited by 0
  21. 2026Context Convergence Improves Answering Inferential Questionscited by 0
  22. 2026Tool-Adaptive LLM Rerankercited by 0
  23. 2026TabRank: Chain-of-Thought Distillation for Table Re-Rankerscited by 0
  24. 2026Evidence Blindness in Direct Corpus Interaction: Persistent Navigation with AtlasNavcited by 0
  25. 2026Beyond Polarization: The Generative Constraint of Chain-of-Thought in Pointwise Rerankingcited by 0
  26. 2026Think Thrice Before Reranking: Multi-perspective Evidence and Reasoning Integration for Text Rerankingcited by 0
  27. 2026Better Nearest Neighbor Graph Indices via (Efficient) LLM-Guided Pruningcited by 0
  28. 2026Component-Aware Feedback for Self-Evolving Programscited by 0
  29. 2026Learning to Retrieve via Reinforcement Learning in Embedding Spacecited by 0
  30. 2026StableJudge: A Lightweight Adversarial Defense Framework for LLM-as-a-Judgecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025R1-Ranker: Teaching LLM Rankers to Reason
  2. 2026Stop Overthinking: Unlocking Efficient Listwise Reranking with Minimal Reasoning
  3. 2025Rank-K: Test-Time Reasoning for Listwise Reranking
  4. 2025REARANK: Reasoning Re-ranking Agent via Reinforcement Learning
  5. 2025Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning
  6. 2026QReason: Query-Focused Decoupled Chain-of-Thought for Efficient Passage Reranking
  7. 2025ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Reranking
  8. 2024RankPrompt: Step-by-Step Comparisons Make Language Models Better Reasoners