# Beyond Distillation: Pushing the Limits of Medical LLM Reasoning with Minimalist Rule-Based RL

arXiv: https://arxiv.org/abs/2505.17952 · HTML: https://mlsanity.com/paper/2505.17952/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 31 of its 52 references that are in the map.
- First posted on arXiv 23 May 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 30 of 31)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training](https://mlsanity.com/paper/2501.17161/) (2025)
- [VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning](https://mlsanity.com/paper/2504.08837/) (2025)
- [BioMistral: A Collection of Open-Source Pretrained Large Language Models for Medical Domains](https://mlsanity.com/paper/2402.10373/) (2024)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [Capabilities of Gemini Models in Medicine](https://mlsanity.com/paper/2404.18416/) (2024)
- [MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding](https://mlsanity.com/paper/2501.18362/) (2025)
- [HuatuoGPT, towards Taming Language Model to Be a Doctor](https://mlsanity.com/paper/2305.15075/) (2023)
- [Continual Pre-training of Language Models](https://mlsanity.com/paper/2302.03241/) (2023)
- [MedVLM-R1: Incentivizing Medical Reasoning Capability of Vision-Language Models (VLMs) via Reinforcement Learning](https://mlsanity.com/paper/2502.19634/) (2025)
- [O1 Replication Journey: A Strategic Progress Report -- Part 1](https://mlsanity.com/paper/2410.18982/) (2024)
- [OpenR: An Open Source Framework for Advanced Reasoning with Large Language Models](https://mlsanity.com/paper/2410.09671/) (2024)
- [ACECODER: Acing Coder RL via Automated Test-Case Synthesis](https://mlsanity.com/paper/2502.01718/) (2025)
- [HuatuoGPT-II, One-stage Training for Medical Adaption of LLMs](https://mlsanity.com/paper/2311.09774/) (2023)
- [Med42 -- Evaluating Fine-Tuning Strategies for Medical LLMs: Full-Parameter vs. Parameter-Efficient Approaches](https://mlsanity.com/paper/2404.14779/) (2024)
- [Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective](https://mlsanity.com/paper/2412.14135/) (2024)
- [m1: Unleash the Potential of Test-Time Scaling for Medical Reasoning with Large Language Models](https://mlsanity.com/paper/2504.00869/) (2025)
- [CoD, Towards an Interpretable Medical Agent using Chain of Diagnosis](https://mlsanity.com/paper/2407.13301/) (2024)
- [MedicalAgentsBench for Complex Medical Reasoning: Comparing Internalized Reasoning Models versus Externalized Agent-based Frameworks](https://mlsanity.com/paper/2503.07459/) (2025)
- [A Preliminary Study of o1 in Medicine: Are We Closer to an AI Doctor?](https://mlsanity.com/paper/2409.15277/) (2024)
- [To Code or not to Code? Adaptive Tool Integration for Math Language Models via Expectation-Maximization](https://mlsanity.com/paper/2502.00691/) (2025)

## Built on by (most cited first, 30 of 36)

- [Baichuan-M2: Scaling Medical Capability with Large Verifier System](https://mlsanity.com/paper/2509.02208/) (2025)
- [SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning](https://mlsanity.com/paper/2506.01713/) (2025)
- [Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning](https://mlsanity.com/paper/2509.03646/) (2025)
- [A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontiers](https://mlsanity.com/paper/2508.21148/) (2025)
- [MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science](https://mlsanity.com/paper/2506.04405/) (2025)
- [InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training](https://mlsanity.com/paper/2510.15859/) (2025)
- [Medical Reasoning in the Era of LLMs: A Systematic Review of Enhancement Techniques and Applications](https://mlsanity.com/paper/2508.00669/) (2025)
- [Fleming-R1: Toward Expert-Level Medical Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2509.15279/) (2025)
- [Stabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalization](https://mlsanity.com/paper/2511.20718/) (2025)
- [DEEPMED: Building a Medical DeepResearch Agent via Multi-hop Med-Search Data and Turn-Controlled Agentic Training & Inference](https://mlsanity.com/paper/2601.18496/) (2026)
- [Evo-MedAgent: Beyond One-Shot Diagnosis with Agents That Remember, Reflect, and Improve](https://mlsanity.com/paper/2604.14475/) (2026)
- [Enhancing Test-Time Scaling of Large Language Models with Hierarchical Retrieval-Augmented MCTS](https://mlsanity.com/paper/2507.05557/) (2025)
- [MedCEG: Reinforcing Verifiable Medical Reasoning with Critical Evidence Graph](https://mlsanity.com/paper/2512.13510/) (2025)
- [GeoRA: Geometry-Aware Low-Rank Adaptation for RLVR](https://mlsanity.com/paper/2601.09361/) (2026)
- [Medical Reasoning with Large Language Models: A Survey and MR-Bench](https://mlsanity.com/paper/2604.08559/) (2026)
- [Med-REFL: Medical Reasoning Enhancement via Self-Corrected Fine-grained Reflection](https://mlsanity.com/paper/2506.13793/) (2025)
- [Scaling Medical Reasoning Verification via Tool-Integrated Reinforcement Learning](https://mlsanity.com/paper/2601.20221/) (2026)
- [Recycling Failures: Salvaging Exploration in RLVR via Fine-Grained Off-Policy Guidance](https://mlsanity.com/paper/2602.24110/) (2026)
- [When Does RL Help Medical VLMs? Disentangling Vision, SFT, and RL Gains](https://mlsanity.com/paper/2603.01301/) (2026)
- [CLR-voyance: Reinforcing Open-Ended Reasoning for Inpatient Clinical Decision Support with Outcome-Aware Rubrics](https://mlsanity.com/paper/2605.09584/) (2026)
- [KAG-Thinker: Interactive Thinking and Deep Reasoning in LLMs via Knowledge-Augmented Generation](https://mlsanity.com/paper/2506.17728/) (2025)
- [Med-R3: Enhancing Medical Retrieval-Augmented Reasoning of LLMs via Progressive Reinforcement Learning](https://mlsanity.com/paper/2507.23541/) (2025)
- [On the Robustness of Answer Formats in Medical Reasoning Models](https://mlsanity.com/paper/2509.20866/) (2025)
- [AdaThink-Med: Optimizing Inference-Time Compute for Medical Reasoning via Uncertainty Quantification](https://mlsanity.com/paper/2509.24560/) (2025)
- [Multilingual Medical Reasoning for Question Answering with Large Language Models](https://mlsanity.com/paper/2512.05658/) (2025)
- [Hint-Guided Diversified Policy Optimization for LLM Reasoning](https://mlsanity.com/paper/2606.03021/) (2026)
- [MedCoAct: Confidence-Aware Multi-Agent Collaboration for Complete Clinical Decision](https://mlsanity.com/paper/2510.10461/) (2025)
- [Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models](https://mlsanity.com/paper/2511.00710/) (2025)
- [Rethinking Multiple-Choice Questions for RLVR: Unlocking Potential via Distractor Design](https://mlsanity.com/paper/2603.12826/) (2026)
- [Process Reward Agents for Steering Knowledge-Intensive Reasoning](https://mlsanity.com/paper/2604.09482/) (2026)

## Abstract (arXiv)

Improving performance on complex tasks and enabling interpretable decision making in large language models (LLMs), especially for clinical applications, requires effective reasoning. Yet this remains challenging without supervised fine-tuning (SFT) on costly chain-of-thought (CoT) data distilled from closed-source models (e.g., GPT-4o). In this work, we present AlphaMed, the first medical LLM to show that reasoning capability can emerge purely through reinforcement learning (RL), using minimalist rule-based rewards on public multiple-choice QA datasets, without relying on SFT or distilled CoT data. AlphaMed achieves state-of-the-art results on six medical QA benchmarks, outperforming models trained with conventional SFT+RL pipelines. On challenging benchmarks (e.g., MedXpert), AlphaMed even surpasses larger or closed-source models such as DeepSeek-V3-671B and Claude-3.5-Sonnet. To understand the factors behind this success, we conduct a comprehensive data-centric analysis guided by three questions: (i) Can minimalist rule-based RL incentivize reasoning without distilled CoT supervision? (ii) How do dataset quantity and diversity impact reasoning? (iii) How does question difficulty shape the emergence and generalization of reasoning? Our findings show that dataset informativeness is a key driver of reasoning performance, and that minimalist RL on informative, multiple-choice QA data is effective at inducing reasoning without CoT supervision. We also observe divergent trends across benchmarks, underscoring limitations in current evaluation and the need for more challenging, reasoning-oriented medical QA benchmarks.