Paper 2603.28589
Towards a Medical AI Scientist
- Published
- Mar 2026
- Research lab
- Independent
- Citations
- 4
- GitHub
- Not linked
01 In brief
Summary
The paper introduces Medical AI Scientist, the first autonomous research framework tailored to clinical medicine.
It generates clinically grounded ideas by transforming surveyed literature into actionable evidence via a clinician-engineer co-reasoning mechanism, and drafts evidence-grounded manuscripts following a structured medical writing paradigm and ethical policies.
The framework operates in three research modes: paper-based reproduction, literature-inspired innovation, and task-driven exploration.
Evaluations by LLMs and human experts across 171 cases, 19 clinical tasks, and 6 data modalities show that its ideas are of substantially higher quality than those from commercial LLMs (GPT-5, Gemini-2.5-Pro).
The system also demonstrates strong alignment between proposed methods and implementations, with higher success rates in executable experiments (up to 0.93 vs.
0.75 for baselines).
Double-blind evaluations by human experts and the Stanford Agentic Reviewer indicate that generated manuscripts approach MICCAI-level quality, surpassing ISBI and BIBM.
One manuscript was accepted at ICAIS 2025.
The system comprises three components: Idea Proposer, Experimental Executor, and Manuscript Composer, supported by the Med-AI Bench benchmark.
Limitations include overly intricate designs, limited experimental depth, and not yet state-of-the-art performance.
02 From the paper
Abstract
Autonomous systems that generate scientific hypotheses, conduct experiments, and draft manuscripts have recently emerged as a promising paradigm for accelerating discovery. However, existing AI Scientists remain largely domain-agnostic, limiting their applicability to clinical medicine, where research is required to be grounded in medical evidence with specialized data modalities. In this work, we introduce Medical AI Scientist, the first autonomous research framework tailored to clinical autonomous research. It enables clinically grounded ideation by transforming extensively surveyed literature into actionable evidence through clinician-engineer co-reasoning mechanism, which improves the traceability of generated research ideas. It further facilitates evidence-grounded manuscript drafting guided by structured medical compositional conventions and ethical policies. The framework operates under 3 research modes, namely paper-based reproduction, literature-inspired innovation, and task-driven exploration, each corresponding to a distinct level of automated scientific inquiry with progressively increasing autonomy. Comprehensive evaluations by both large language models and human experts demonstrate that the ideas generated by the Medical AI Scientist are of substantially higher quality than those produced by commercial LLMs across 171 cases, 19 clinical tasks, and 6 data modalities. Meanwhile, our system achieves strong alignment between the proposed method and its implementation, while also demonstrating significantly higher success rates in executable experiments. Double-blind evaluations by human experts and the Stanford Agentic Reviewer suggest that the generated manuscripts approach MICCAI-level quality, while consistently surpassing those from ISBI and BIBM. The proposed Medical AI Scientist highlights the potential of leveraging AI for autonomous scientific discovery in healthcare.