# R2MED: A Benchmark for Reasoning-Driven Medical Retrieval

arXiv: https://arxiv.org/abs/2505.14558 · HTML: https://mlsanity.com/paper/2505.14558/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2025.

## Built on by (most cited first, 22 of 22)

- [ReasonEmbed: Enhanced Text Embeddings for Reasoning-Intensive Document Retrieval](https://mlsanity.com/paper/2510.08252/) (2025)
- [Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications](https://mlsanity.com/paper/2508.00669/) (2025)
- [Unlocking Multimodal Document Intelligence: From Current Triumphs to Future Frontiers of Visual Document Retrieval](https://mlsanity.com/paper/2602.19961/) (2026)
- [Benchmarking Information Retrieval Models on Complex Retrieval Tasks](https://mlsanity.com/paper/2509.07253/) (2025)
- [PaperSearchQA: Learning to Search and Reason over Scientific Papers with RLVR](https://mlsanity.com/paper/2601.18207/) (2026)
- [TFRank: Think-Free Reasoning Enables Practical Pointwise LLM Ranking](https://mlsanity.com/paper/2508.09539/) (2025)
- [SoREX: Towards Self-Explainable Social Recommendation with Relevant Ego-Path Extraction](https://mlsanity.com/paper/2510.00080/) (2025)
- [Inflated Excellence or True Performance? Rethinking Medical Diagnostic Benchmarks with Dynamic Evaluation](https://mlsanity.com/paper/2510.09275/) (2025)
- [InsertRank: LLMs can reason over BM25 scores to Improve Listwise Reranking](https://mlsanity.com/paper/2506.14086/) (2025)
- [GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs](https://mlsanity.com/paper/2511.11653/) (2025)
- [HypeMed: Enhancing Medication Recommendations with Hypergraph-Based Patient Relationships](https://mlsanity.com/paper/2603.18459/) (2026)
- [The Path to Self-Evolving Clinical Systems: Scaling Medical Agents from Assistance to Autonomy](https://mlsanity.com/paper/2607.11175/) (2026)
- [Lighting the Way for BRIGHT: Reproducible Baselines with Anserini, Pyserini, and RankLLM](https://mlsanity.com/paper/2509.02558/) (2025)
- [A Survey of Reasoning-Intensive Retrieval: Progress and Challenges](https://mlsanity.com/paper/2605.00063/) (2026)
- [AR-Med: Automated Relevance Enhancement in Medical Search via LLM-Driven Information Augmentation](https://mlsanity.com/paper/2512.03737/) (2025)
- [Asking the Right Questions: Ontology-Grounded Interpretable Embeddings for Biomedical Text](https://mlsanity.com/paper/2603.01690/) (2026)
- [HAKARI-Bench: A Lightweight Benchmark for Comparing Retrieval Architectures and Efficiency Settings under Unified Conditions](https://mlsanity.com/paper/2606.22778/) (2026)
- [H+ Embedding: Harmonizing Global and Token-Level Retrieval with Context-Dependent Phrases](https://mlsanity.com/paper/2608.00065/) (2026)
- [Controllable Affective Generation via Latent Vector Steering](https://mlsanity.com/paper/2608.25569/) (2026)
- [OntologyBench: Can Dense Retrieval Satisfy Structured Biomedical Constraints?](https://mlsanity.com/paper/2609.08174/) (2026)
- [From Static Personal Values to Contextualized Personalization: Bayesian Personalized Value Alignment for LLMs](https://mlsanity.com/paper/2609.28942/) (2026)
- [A Living Benchmark for Information Retrieval from Electronic Health Records](https://mlsanity.com/paper/2609.30205/) (2026)

## Abstract (arXiv)

Current medical retrieval benchmarks primarily emphasize lexical or shallow semantic similarity, overlooking the reasoning-intensive demands that are central to clinical decision-making. In practice, physicians often retrieve authoritative medical evidence to support diagnostic hypotheses. Such evidence typically aligns with an inferred diagnosis rather than the surface form of a patient's symptoms, leading to low lexical or semantic overlap between queries and relevant documents. To address this gap, we introduce R2MED, the first benchmark explicitly designed for reasoning-driven medical retrieval. It comprises 876 queries spanning three tasks: Q&A reference retrieval, clinical evidence retrieval, and clinical case retrieval. These tasks are drawn from five representative medical scenarios and twelve body systems, capturing the complexity and diversity of real-world medical information needs. We evaluate 15 widely-used retrieval systems on R2MED and find that even the best model achieves only 31.4 nDCG@10, demonstrating the benchmark's difficulty. Classical re-ranking and generation-augmented retrieval methods offer only modest improvements. Although large reasoning models improve performance via intermediate inference generation, the best results still peak at 41.4 nDCG@10. These findings underscore a substantial gap between current retrieval techniques and the reasoning demands of real clinical tasks. We release R2MED as a challenging benchmark to foster the development of next-generation medical retrieval systems with enhanced reasoning capabilities. Data and code are available at https://github.com/R2MED/R2MED