mlsanityData to 14 Oct 2026

REARANK: Reasoning Re-ranking Agent via Reinforcement Learning

arXiv 2505.20046 ↗First posted 26 May 2025cs.IR cs.CLcited by 24

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

also in 1 more
Abstract (arXiv)

We present REARANK, a large language model (LLM)-based listwise reasoning reranking agent. REARANK explicitly reasons before reranking, significantly improving both performance and interpretability. Leveraging reinforcement learning and data augmentation, REARANK achieves substantial improvements over baseline models across popular information retrieval benchmarks, notably requiring only 179 annotated samples. Built on top of Qwen2.5-7B, our REARANK-7B demonstrates performance comparable to GPT-4 on both in-domain and out-of-domain benchmarks and even surpasses GPT-4 on reasoning-intensive BRIGHT benchmarks. These results underscore the effectiveness of our approach and highlight how reinforcement learning can enhance LLM reasoning capabilities in reranking.

Key facts. Cited by 24 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 30 of its 43 references that are in the map. First posted on arXiv 26 May 2025.

Builds on

30 of 43 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Rank-R1: Enhancing Reasoning in LLM-based Document Rerankers via Reinforcement Learning8 Mar

Other references · 29

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  4. 2025Qwen3 Technical Reportcited by 8,820
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,708
  7. 2024Qwen2.5 Technical Reportcited by 4,942
  8. 2022Emergent Abilities of Large Language Modelscited by 2,512
  9. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  10. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  11. 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,252
  12. 2020Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrievalcited by 849
17 more
  1. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 593
  2. 2025LIMO: Less is More for Reasoningcited by 498
  3. 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 472
  4. 2024LLM2Vec: Large Language Models Are Secretly Powerful Text Encoderscited by 404
  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. 2022Improving Passage Retrieval with Zero-Shot Question Generationcited by 165
  9. 2024BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrievalcited by 158
  10. 2023RankZephyr: Effective and Robust Zero-Shot Listwise Reranking is a Breeze!cited by 155
  11. 2022Holistic Evaluation of Language Modelscited by 131
  12. 2025DeepSeek-R1 Thoughtology: Let's think about LLM Reasoningcited by 92
  13. 2023Zero-Shot Listwise Document Reranking with a Large Language Modelcited by 82
  14. 2023RankVicuna: Zero-Shot Listwise Document Reranking with Open-Source Large Language Modelscited by 70
  15. 2024Assessing and Learning Alignment of Unimodal Vision and Language Modelscited by 32
  16. 2024Exploring the Best Practices of Query Expansion with Large Language Modelscited by 17
  17. 2023MoqaGPT : Zero-Shot Multi-modal Open-domain Question Answering with Large Language Modelcited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 12; 2026: 12.

24 papers.

Sort:

By area:

  1. 2025DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrievalcited by 37
  2. 2025It Takes Two: Your GRPO Is Secretly DPOcited by 26
  3. 2025Mano Technical Reportcited by 13
  4. 2025Optimizing Generative Ranking Relevance via Reinforcement Learning in Xiaohongshu Searchcited by 11
  5. 2026GR2: Generative Reasoning Re-rankercited by 11
  6. 2025Rethinking Reasoning in Document Ranking: Why Chain-of-Thought Falls Shortcited by 7
  7. 2026Recursive Self-Evolving Agents via Held-Out Selectioncited by 7
  8. 2026RoboRouter: Training-Free Policy Routing for Robotic Manipulationcited by 6
  9. 2025SciRerankBench: Benchmarking Rerankers Towards Scientific Retrieval-Augmented Generated LLMscited by 5
  10. 2025TFRank: Think-Free Reasoning Enables Practical Pointwise LLM Rankingcited by 5
  11. 2026MemSifter: Offloading LLM Memory Retrieval via Outcome-Driven Proxy Reasoningcited by 3
  12. 2026Beyond Relevance-Centric Retrieval: Rubric-Oriented Document Set Selection and Rankingcited by 3
12 more
  1. 2025CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generationcited by 2
  2. 2025LoRALib: A Standardized Benchmark for Evaluating LoRA-MoE Methodscited by 1
  3. 2025ToM: Leveraging Tree-oriented MapReduce for Long-Context Reasoning in Large Language Modelscited by 1
  4. 2026The Past Is Not Past: Memory-Enhanced Dynamic Reward Shapingcited by 1
  5. 2026AdaTutoRank: Learning to Rerank Document Sets via Adaptive Tutoring Optimization for RAG and Deep Researchcited by 1
  6. 2025DeepCodeSeek: Real-Time API Retrieval for Context-Aware Code Generationcited by 0
  7. 2025LIR3AG: A Lightweight Rerank Reasoning Strategy Framework for Retrieval-Augmented Generationcited by 0
  8. 2026GR2 Technical Reportcited by 0
  9. 2026Diffusion-GR2: Diffusion Generative Reasoning Re-rankercited by 0
  10. 2026HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Modelscited by 0
  11. 2026Better Nearest Neighbor Graph Indices via (Efficient) LLM-Guided Pruningcited by 0
  12. 2026Component-Aware Feedback for Self-Evolving Programscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025R1-Ranker: Teaching LLM Rankers to Reason
  2. 2025ReasonRank: Empowering Passage Ranking with Strong Reasoning Ability
  3. 2026Tool-Adaptive LLM Reranker
  4. 2025DynamicRAG: Leveraging Outputs of Large Language Model as Feedback for Dynamic Reranking in Retrieval-Augmented Generation
  5. 2025Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking
  6. 2026QReason: Query-Focused Decoupled Chain-of-Thought for Efficient Passage Reranking
  7. 2025ProRank: Prompt Warmup via Reinforcement Learning for Small Language Models Reranking
  8. 2026Stop Overthinking: Unlocking Efficient Listwise Reranking with Minimal Reasoning