mlsanityData to 14 Oct 2026

RaDeR: Reasoning-aware Dense Retrieval Models

arXiv 2505.18405 ↗First posted 23 May 2025cs.CL cs.IRcited by 27

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

Abstract (arXiv)

We propose RaDeR, a set of reasoning-based dense retrieval models trained with data derived from mathematical problem solving using large language models (LLMs). Our method leverages retrieval-augmented reasoning trajectories of an LLM and self-reflective relevance evaluation, enabling the creation of both diverse and hard-negative samples for reasoning-intensive relevance. RaDeR retrievers, trained for mathematical reasoning, effectively generalize to diverse reasoning tasks in the BRIGHT and RAR-b benchmarks, consistently outperforming strong baselines in overall performance. Notably, RaDeR achieves significantly higher performance than baselines on the Math and Coding splits. In addition, RaDeR presents the first dense retriever that outperforms BM25 when queries are Chain-of-Thought reasoning steps, underscoring the critical role of reasoning-based retrieval to augment reasoning language models. Furthermore, RaDeR achieves comparable or superior performance while using only 2.5% of the training data used by the concurrent work REASONIR, highlighting the quality of our synthesized training data.

Key facts. Cited by 27 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 26 of its 53 references that are in the map. First posted on arXiv 23 May 2025.

Builds on

26 of 53 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025ReasonIR: Training Retrievers for Reasoning Tasks29 Apr
  2. 2025Distillation and Refinement of Reasoning in Small Language Models for Document Re-ranking4 Apr
  3. 2025MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Search26 Mar
  4. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning12 Mar
  5. 2025R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning7 Mar
  6. 2025Rank1: Test-Time Compute for Reranking in Information Retrieval25 Feb
  7. 2024RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Models3 Dec
  8. 2024RAR-b: Reasoning as Retrieval Benchmark9 Apr
  9. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions20 Dec

Other references · 17

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  5. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  6. 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,605
  7. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  8. 2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinkingcited by 313
  9. 2023Fine-Tuning LLaMA for Multi-Stage Text Retrievalcited by 272
  10. 2024Generative Representational Instruction Tuningcited by 233
  11. 2024BRIGHT: A Realistic and Challenging Benchmark for Reasoning-Intensive Retrievalcited by 158
  12. 2022SimLM: Pre-training with Representation Bottleneck for Dense Passage Retrievalcited by 90
5 more
  1. 2024Gecko: Versatile Text Embeddings Distilled from Large Language Modelscited by 83
  2. 2024Reliable, Adaptable, and Attributable Language Models with Retrievalcited by 73
  3. 2022InPars: Data Augmentation for Information Retrieval using Large Language Modelscited by 62
  4. 2025Tevatron 2.0: Unified Document Retrieval Toolkit across Scale, Language, and Modalitycited by 30
  5. 2024SeRTS: Self-Rewarding Tree Search for Biomedical Retrieval-Augmented Generationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 19.

27 papers.

Sort:

By area:

  1. 2025DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrievalcited by 37
  2. 2025ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrievalcited by 16
  3. 2025MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark for Reasoning-Intensive Multimodal Retrievalcited by 12
  4. 2026LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Provingcited by 10
  5. 2025Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigmcited by 9
  6. 2025Abductive Inference in Retrieval-Augmented Language Models: Generating and Validating Missing Premisescited by 9
  7. 2026LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrievalcited by 9
  8. 2026Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrievalcited by 8
  9. 2026MathNet: a Global Multimodal Benchmark for Mathematical Reasoning and Retrievalcited by 6
  10. 2025Think Before You Retrieve: Learning Test-Time Adaptive Search with Small Language Modelscited by 5
  11. 2025A Vision for Geo-Temporal Deep Research Systems: Towards Comprehensive, Transparent, and Reproducible Geo-Temporal Information Synthesiscited by 2
  12. 2026Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systemscited by 2
15 more
  1. 2026RICE-PO: Turning Retrieval Interactions into Credit Signals for Reasoning Agentscited by 2
  2. 2026RL-Index: Reinforcement Learning for Retrieval Index Reasoningcited by 2
  3. 2026Antares: Foundation Models for Agentic Vulnerability Localizationcited by 2
  4. 2026Latent Abstraction for Retrieval-Augmented Generationcited by 1
  5. 2026SABER-Math: Automated Benchmark for Information Retrieval Evaluation in Mathematicscited by 1
  6. 2026The Magnitude Mirage: Rethinking Confidence for Reasoning-Intensive Retrievalcited by 1
  7. 2025PathFinder: MCTS and LLM Feedback-based Path Selection for Multi-Hop Question Answeringcited by 0
  8. 2026Inferential Question Answeringcited by 0
  9. 2026CRE-T1 Preview Technical Report: Beyond Contrastive Learning for Reasoning-Intensive Retrievalcited by 0
  10. 2026MARVEL: Multimodal Adaptive Reasoning-intensiVe Expand-rerank and retrievaLcited by 0
  11. 2026BRIDGE: Multimodal-to-Text Retrieval via Reinforcement-Learned Query Alignmentcited by 0
  12. 2026HIVE: Query, Hypothesize, Verify An LLM Framework for Multimodal Reasoning-Intensive Retrievalcited by 0
  13. 2026Context Convergence Improves Answering Inferential Questionscited by 0
  14. 2026Retrieval Grounding Latent Reasoning for Dense Retrievalcited by 0
  15. 2026Better Nearest Neighbor Graph Indices via (Efficient) LLM-Guided Pruningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026A Survey of Reasoning-Intensive Retrieval: Progress and Challenges
  2. 2025Your Dense Retriever is Secretly an Expeditious Reasoner
  3. 2024NeedleBench: Evaluating LLM Retrieval and Reasoning Across Varying Information Densities
  4. 2025Retrieval-Augmented Process Reward Model for Generalizable Mathematical Reasoning
  5. 2026When to Retrieve During Reasoning: Adaptive Retrieval for Large Reasoning Models
  6. 2026Adaptive Retrieval helps Reasoning in LLMs -- but mostly if it's not used
  7. 2026ROG: Retrieval-Augmented LLM Reasoning for Complex First-Order Queries over Knowledge Graphs
  8. 2025Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoning