# MedReflect: Teaching Medical LLMs to Self-Improve via Reflective Correction

arXiv: https://arxiv.org/abs/2510.03687 · HTML: https://mlsanity.com/paper/2510.03687/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Placed in Medical synthetic data and agents, one of 13 directions in Synthetic data and self-improvement for LLMs.
- Builds on 25 of its 43 references that are in the map.
- First posted on arXiv 4 Oct 2025.

## Placed in

- Synthetic data and self-improvement for LLMs / [Medical synthetic data and agents](https://mlsanity.com/synth/medical-synthetic-data-and-agents/)

## Builds on (most cited first, 25 of 25)

- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark](https://mlsanity.com/paper/2406.01574/) (2024)
- [Gemma 3 Technical Report](https://mlsanity.com/paper/2503.19786/) (2025)
- [What Disease does this Patient Have? A Large-scale Open Domain Question Answering Dataset from Medical Exams](https://mlsanity.com/paper/2009.13081/) (2020)
- [PubMedQA: A Dataset for Biomedical Research Question Answering](https://mlsanity.com/paper/1909.06146/) (2019)
- [ChatDoctor: A Medical Chat Model Fine-Tuned on a Large Language Model Meta-AI (LLaMA) Using Medical Domain Knowledge](https://mlsanity.com/paper/2303.14070/) (2023)
- [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)
- [When Can LLMs Actually Correct Their Own Mistakes? A Critical Survey of Self-Correction of LLMs](https://mlsanity.com/paper/2406.01297/) (2024)
- [Recursive Introspection: Teaching Language Model Agents How to Self-Improve](https://mlsanity.com/paper/2407.18219/) (2024)
- [Stream of Search (SoS): Learning to Search in Language](https://mlsanity.com/paper/2404.03683/) (2024)
- [MedReason: Eliciting Factual Medical Reasoning Steps in LLMs via Knowledge Graphs](https://mlsanity.com/paper/2504.00993/) (2025)
- [SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales](https://mlsanity.com/paper/2405.20974/) (2024)
- [HuatuoGPT-II, One-stage Training for Medical Adaption of LLMs](https://mlsanity.com/paper/2311.09774/) (2023)
- [UltraMedical: Building Specialized Generalists in Biomedicine](https://mlsanity.com/paper/2406.03949/) (2024)
- [Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision](https://mlsanity.com/paper/2411.16579/) (2024)
- [Physics of Language Models: Part 2.2, How to Learn From Mistakes on Grade-School Math Problems](https://mlsanity.com/paper/2408.16293/) (2024)
- [Large Language Models are Clinical Reasoners: Reasoning-Aware Diagnosis Framework with Prompt-Generated Rationales](https://mlsanity.com/paper/2312.07399/) (2023)
- [To Backtrack or Not to Backtrack: When Sequential Search Limits Model Reasoning](https://mlsanity.com/paper/2504.07052/) (2025)
- [On the Emergence of Thinking in LLMs I: Searching for the Right Intuition](https://mlsanity.com/paper/2502.06773/) (2025)
- [MedREQAL: Examining Medical Knowledge Recall of Large Language Models via Question Answering](https://mlsanity.com/paper/2406.05845/) (2024)
- [From Emergence to Control: Probing and Modulating Self-Reflection in Language Models](https://mlsanity.com/paper/2506.12217/) (2025)
- [DoctorRAG: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients](https://mlsanity.com/paper/2505.19538/) (2025)
- [MedFact-R1: Towards Factual Medical Reasoning via Pseudo-Label Augmentation](https://mlsanity.com/paper/2509.15154/) (2025)

## Built on by (most cited first, 8 of 8)

- [When Models Learn to Ask Why: Adaptive Causal Reasoning for Trustworthy Medical Vision-Language Models](https://mlsanity.com/paper/2603.23085/) (2026)
- [Self-Improvement of Large Language Models: A Technical Overview and Future Outlook](https://mlsanity.com/paper/2603.25681/) (2026)
- [Can Large Language Models Self-Correct in Medical Question Answering? An Exploratory Study](https://mlsanity.com/paper/2604.00261/) (2026)
- [PACE-RAG: Patient-Aware Contextual and Evidence-Constrained RAG for Clinical Drug Recommendation](https://mlsanity.com/paper/2603.17356/) (2026)
- [Echo-CoPilot: A Multiple-Perspective Agentic Framework for Reliable Echocardiography Interpretation](https://mlsanity.com/paper/2512.09944/) (2025)
- [Readable but Not Controllable: Neuron-Level Evidence for Medical LLM Hallucination](https://mlsanity.com/paper/2607.00158/) (2026)
- [The Rise of Verbal Reinforcement Learning](https://mlsanity.com/paper/2609.01597/) (2026)
- [Constructing and Evaluating Clinical Reasoning Trajectories for Medical Agent](https://mlsanity.com/paper/2609.05090/) (2026)

## Abstract (arXiv)

Medical problem-solving demands expert knowledge and intricate reasoning. Recent studies of large language models (LLMs) attempt to ease this complexity by introducing external knowledge verification through retrieval-augmented generation or by training on reasoning datasets. However, these approaches suffer from drawbacks such as retrieval overhead and high annotation costs, and they heavily rely on substituted external assistants to reach limited performance in medical field. In this paper, we introduce MedReflect, a generalizable framework designed to inspire LLMs with a physician-like reflective thinking mode. MedReflect generates a single-pass reflection chain that includes initial hypothesis generation, self-questioning, self-answering and decision refinement. This self-verified and self-reflective nature releases large language model's latent capability in medical problem-solving without external retrieval or heavy annotation. We demonstrate that MedReflect enables cost-efficient medical dataset construction. With only a minimal subset of randomly sampled training examples and lightweight fine-tuning, this approach achieves notable absolute accuracy improvements across a series of medical benchmarks while significantly cutting annotation requirements. Our results provide evidence that LLMs can learn to solve specialized medical problems via self-reflection and self-improvement, reducing reliance on external supervision and extensive task-specific fine-tuning data.