# ReasonIR: Training Retrievers for Reasoning Tasks

arXiv: https://arxiv.org/abs/2504.20595 · HTML: https://mlsanity.com/paper/2504.20595/

## Key facts

- Cited by 77 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 56 of its 65 references that are in the map.
- First posted on arXiv 29 Apr 2025.

## Placed in

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

## Builds on (most cited first, 30 of 56)

- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Measuring Massive Multitask Language Understanding](https://mlsanity.com/paper/2009.03300/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [SQuAD: 100,000+ Questions for Machine Comprehension of Text](https://mlsanity.com/paper/1606.05250/) (2016)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [TriviaQA: A Large Scale Distantly Supervised Challenge Dataset for Reading Comprehension](https://mlsanity.com/paper/1705.03551/) (2017)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Self-Instruct: Aligning Language Models with Self-Generated Instructions](https://mlsanity.com/paper/2212.10560/) (2022)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [MS MARCO: A Human Generated MAchine Reading COmprehension Dataset](https://mlsanity.com/paper/1611.09268/) (2016)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Least-to-Most Prompting Enables Complex Reasoning in Large Language Models](https://mlsanity.com/paper/2205.10625/) (2022)
- [FEVER: a large-scale dataset for Fact Extraction and VERification](https://mlsanity.com/paper/1803.05355/) (2018)
- [Improving language models by retrieving from trillions of tokens](https://mlsanity.com/paper/2112.04426/) (2021)
- [Unsupervised Dense Information Retrieval with Contrastive Learning](https://mlsanity.com/paper/2112.09118/) (2021)
- [Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questions](https://mlsanity.com/paper/2212.10509/) (2022)
- [Distilling Step-by-Step! Outperforming Larger Language Models with Less Training Data and Smaller Model Sizes](https://mlsanity.com/paper/2305.02301/) (2023)
- [Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models](https://mlsanity.com/paper/2309.01219/) (2023)
- [Contrastive Learning with Hard Negative Samples](https://mlsanity.com/paper/2010.04592/) (2020)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Search-o1: Agentic Search-Enhanced Large Reasoning Models](https://mlsanity.com/paper/2501.05366/) (2025)
- [Hard Negative Mixing for Contrastive Learning](https://mlsanity.com/paper/2010.01028/) (2020)
- [Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents](https://mlsanity.com/paper/2304.09542/) (2023)
- [R1-Searcher: Incentivizing the Search Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2503.05592/) (2025)
- [Improving Text Embeddings with Large Language Models](https://mlsanity.com/paper/2401.00368/) (2023)
- [Fine-Tuning LLaMA for Multi-Stage Text Retrieval](https://mlsanity.com/paper/2310.08319/) (2023)
- [Nomic Embed: Training a Reproducible Long Context Text Embedder](https://mlsanity.com/paper/2402.01613/) (2024)
- [Promptagator: Few-shot Dense Retrieval From 8 Examples](https://mlsanity.com/paper/2209.11755/) (2022)

## Built on by (most cited first, 30 of 77)

- [ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory](https://mlsanity.com/paper/2509.25140/) (2025)
- [BrowseComp-Plus: A More Fair and Transparent Evaluation Benchmark of Deep-Research Agent](https://mlsanity.com/paper/2508.06600/) (2025)
- [Seq vs Seq: An Open Suite of Paired Encoders and Decoders](https://mlsanity.com/paper/2507.11412/) (2025)
- [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)
- [RaDeR: Reasoning-aware Dense Retrieval Models](https://mlsanity.com/paper/2505.18405/) (2025)
- [A Comprehensive Survey on Reinforcement Learning-based Agentic Search: Foundations, Roles, Optimizations, Evaluations, and Applications](https://mlsanity.com/paper/2510.16724/) (2025)
- [AgentIR: Reasoning-Aware Retrieval for Deep Research Agents](https://mlsanity.com/paper/2603.04384/) (2026)
- [ThinkQE: Query Expansion via an Evolving Thinking Process](https://mlsanity.com/paper/2506.09260/) (2025)
- [MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark for Reasoning-Intensive Multimodal Retrieval](https://mlsanity.com/paper/2510.09510/) (2025)
- [TongSearch-QR: Reinforced Query Reasoning for Retrieval](https://mlsanity.com/paper/2506.11603/) (2025)
- [Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient?](https://mlsanity.com/paper/2605.10848/) (2026)
- [LeanSearch v2: Global Premise Retrieval for Lean 4 Theorem Proving](https://mlsanity.com/paper/2605.13137/) (2026)
- [Large Reasoning Embedding Models: Towards Next-Generation Dense Retrieval Paradigm](https://mlsanity.com/paper/2510.14321/) (2025)
- [LaSER: Internalizing Explicit Reasoning into Latent Space for Dense Retrieval](https://mlsanity.com/paper/2603.01425/) (2026)
- [Frustratingly Simple Retrieval Improves Challenging, Reasoning-Intensive Benchmarks](https://mlsanity.com/paper/2507.01297/) (2025)
- [AI-SearchPlanner: Modular Agentic Search via Pareto-Optimal Multi-Objective Reinforcement Learning](https://mlsanity.com/paper/2508.20368/) (2025)
- [EviNote-RAG: Enhancing RAG Models via Answer-Supportive Evidence Notes](https://mlsanity.com/paper/2509.00877/) (2025)
- [Don't "Overthink" Passage Reranking: Is Reasoning Truly Necessary?](https://mlsanity.com/paper/2505.16886/) (2025)
- [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)
- [Revisiting Text Ranking in Deep Research](https://mlsanity.com/paper/2602.21456/) (2026)
- [Procedural Knowledge at Scale Improves Reasoning](https://mlsanity.com/paper/2604.01348/) (2026)
- [FutureSim: Replaying World Events to Evaluate Adaptive Agents](https://mlsanity.com/paper/2605.15188/) (2026)
- [ERank: Fusing Supervised Fine-Tuning and Reinforcement Learning for Effective and Efficient Text Reranking](https://mlsanity.com/paper/2509.00520/) (2025)
- [Benchmarking Information Retrieval Models on Complex Retrieval Tasks](https://mlsanity.com/paper/2509.07253/) (2025)
- [TEMPO: A Realistic Multi-Domain Benchmark for Temporal Reasoning-Intensive Retrieval](https://mlsanity.com/paper/2601.09523/) (2026)
- [LLMs Should Express Uncertainty Explicitly](https://mlsanity.com/paper/2604.05306/) (2026)
- [TFRank: Think-Free Reasoning Enables Practical Pointwise LLM Ranking](https://mlsanity.com/paper/2508.09539/) (2025)
- [Beyond Sequential Reranking: Reranker-Guided Search Improves Reasoning Intensive Retrieval](https://mlsanity.com/paper/2509.07163/) (2025)

## Abstract (arXiv)

We present ReasonIR-8B, the first retriever specifically trained for general reasoning tasks. Existing retrievers have shown limited gains on reasoning tasks, in part because existing training datasets focus on short factual queries tied to documents that straightforwardly answer them. We develop a synthetic data generation pipeline that, for each document, our pipeline creates a challenging and relevant query, along with a plausibly related but ultimately unhelpful hard negative. By training on a mixture of our synthetic data and existing public data, ReasonIR-8B achieves a new state-of-the-art of 29.9 nDCG@10 without reranker and 36.9 nDCG@10 with reranker on BRIGHT, a widely-used reasoning-intensive information retrieval (IR) benchmark. When applied to RAG tasks, ReasonIR-8B improves MMLU and GPQA performance by 6.4% and 22.6% respectively, relative to the closed-book baseline, outperforming other retrievers and search engines. In addition, ReasonIR-8B uses test-time compute more effectively: on BRIGHT, its performance consistently increases with longer and more information-rich rewritten queries; it continues to outperform other retrievers when combined with an LLM reranker. Our training recipe is general and can be easily extended to future LLMs; to this end, we open-source our code, data, and model.