cs.AIMar 30, 2026

Towards a Medical AI Scientist

Authors: Hongtao Wu, Boyun Zheng, Dingjie Song, Yu Jiang, Jianfeng Gao, Lei Xing, Lichao Sun, Yixuan Yuan

Organizations: The Chinese University of Hong Kong · Lehigh University · Microsoft Research · Stanford University

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this 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.

Figures & tables

Figure 1: a, System workflow: fully-automated multi-agents system for end-to-end scientific discovery in clinical medicine. b, Med-AI Bench: visualization depicting 19 distinct medical research tasks within performance benchmarking. c, Experimental setup: comparative evaluation across Idea generation, execution and full paper compilation in the research lifecycle. d, Performance benchmarking: comparable manuscript quality to representative works from leading venues.
Figure 2: Medical AI Scientist surpasses commercial LLMs in idea generation under combined LLM-based and blinded human evaluation. Models generated research ideas that were anonymized and assessed by three independent experts using a five point scale. a, LLM based evaluation of idea quality. b, Quantitative human assessment across six evaluation criteria. c, Qualitative human analysis of strengths and limitations relative to commercial LLMs.
Figure 3: Example of idea generation comparison between Medical AI Scientist and commercial LLMs in the Literature-inspired Innovation Mode.
Figure 4: Comparative evaluation of Medical AI Scientist frameworks against commercial LLMs in terms of implementation completeness and experimental success rate. a, Implementation completeness was assessed on a five point scale ranging from 1 to 5. Model generated outputs were anonymized and independently evaluated by two LLM-based judges. b, Experimental success rate measured through quantitative human evaluation.
Figure 5: Anonymized comparison of paper quality on an identical medical task. Manuscripts generated by Medical AI Scientist achieve performance comparable to MICCAI, ISBI, and BIBM under consistent double-blind evaluation across both quantitative and qualitative assessments: a, Stanford Agentic Reviewer automatic evaluation. b, Double-blinded scoring (1–5) by 10 medical experts (PhD/postdoc) across five review dimensions. c, Experts’ observations on strengths and limitations.
Figure 6: The conceptual illustration of the Medical AI Scientist: A comprehensive system of fully-automated agents for end-to-end scientific discovery in clinical medicine. The system offers three user interaction modes: Reproduction (reproducing a specified hypothesis), Innovation (innovating from provided literature) and Exploration (autonomously exploring a given research direction), to streamline medical research process. The workflow consists of several phases covering automated idea generation, experiment execution, manuscript writing.
Figure A.1 : Example of Medical AI Scientist Innovation Mode on the medical image classification task. All necessary processes and outcomes are presented, with human expert’s notes in bottom boxes.
Figure A.2 : Example of Medical AI Scientist Exploration Mode on the medical video restoration task. All necessary processes and outcomes are presented, with human expert’s notes in bottom boxes.
More in this topic

AI Agents for Scientific Discovery

AI agents for scientific discovery use language models, tools, and experiments to generate, test, and refine scientific knowledge.

See all 287 papers

Explore similar work

CardsList
Sep 17, 2026

ScientistTwo: Pioneering the Human Knowledge Frontier with Autonomous AI

Scientific discovery is defined by the ability to identify the boundaries of existing knowledge and venture into unexplored territory. The ultimate vision for AI in science is problem-driven autonomous research: given a fundamental challenge by a human expert, the AI independently navigates the scientific landscape, uncovers theoretical and empirical bottlenecks, and systematically expands the frontier of knowledge. In this paper, we introduce ScientistTwo, a fully autonomous multi-agent framework designed to realize this vision. Specifically, ScientistTwo takes an initial problem as input, establishes state-of-the-art baselines, formulates novel hypotheses, and coordinates specialized agents to orchestrate an end-to-end discovery cycle without human intervention. Moreover, the framework rigorously conducts experiments using diverse datasets and metrics, refines methodologies through automated ablation studies, and validates research findings via a closed-loop simulated peer-review rebuttal engine. To evaluate ScientistTwo's capabilities against the highest standards of human scientific achievement, we benchmark it across papers accepted at top-tier conferences such as ICLR, ICML, and NeurIPS. As a result, ScientistTwo autonomously generates expert-level, publishable papers and fully verified, executable codebases. Its solutions consistently outperform human state-of-the-art models, and achieve higher average review ratings than human-authored papers under automated AI review agents. These results show that ScientistTwo is not merely an assistive tool but an autonomous scientific pioneer capable of pushing the frontiers of human discovery. Project website: https://scientist-two.github.io/

Jaehyun Nam, Jinsung Yoon, Yanzhou Pan +4

Google Cloud AI Research · University of Waterloo

Scientific Hypothesis GenerationMulti-Agent SystemsAutonomous Scientific DiscoveryAutonomous Research Agents
AskPDF
Mar 31, 2026

Towards End-to-End Automation of AI Research

The automation of science is a long-standing ambition in the field of AI. While the community has made significant progress in automating individual components of the scientific process, a system that autonomously navigates the entire research lifecycle -- from conception to publication -- has remained out of reach. Here, we present the strongest demonstration to date toward automating the entire process end-to-end. We present The AI Scientist, which creates research ideas, writes code, runs experiments, plots and analyzes data, writes the entire scientific manuscript and performs its own peer review. Its ideas, execution, and presentation are of sufficient quality to produce a manuscript generated by an AI system that passes the first round of peer review at a major machine learning conference workshop. The workshop has an acceptance rate of 70 percent. Our system leverages modern foundation models within a complex agentic system. We evaluate The AI Scientist in two settings: a focused mode using human-provided code templates as an initial scaffold to conduct research on a specific topic, and a template-free, open-ended mode that leverages agentic search for wider scientific exploration. Both settings produce diverse ideas and automatically test, report on, and evaluate them. This achievement demonstrates AI's growing capacity for scientific contribution and signifies a potential paradigm shift in how research is conducted. As with any impactful new technology, there could be significant risks, including taxing overwhelmed review systems and adding noise to scientific literature. However, if developed responsibly, such autonomous systems could greatly accelerate scientific discovery.

Yutaro Yamada, Robert Tjarko Lange, Cong Lu +5

Sakana AI, Tokyo, Japan · University of British Columbia, Vancouver, Canada · Vector Institute, Toronto, Canada +1

AI-Assisted Scientific ResearchAutonomous Scientific DiscoveryAutonomous Research AgentsScientific Workflow Automation
AskPDF
Aug 13, 2026

OmniScientist: An Omni-Modal Omni-Discipline AI Scientist

Recent advances in foundation models have enabled AI scientists to automate increasingly complete research workflows, from hypothesis generation and code execution to manuscript preparation. Yet workflow coverage alone does not provide access to the full evidence on which scientific discovery depends. Existing systems typically reason over text, code, labels, or precomputed summaries, leaving scientifically decisive spatial, temporal, cross-channel, and procedural relations unavailable to the agent. We introduce OmniScientist, an end-to-end, omni-modal AI scientist that conducts multidisciplinary research directly from heterogeneous raw evidence. A perception layer and 3 autonomous agents for ideation, experiment, and writeup operate within a deterministic pipeline, allowing observations to shape research questions, experimental decisions, and final claims throughout the research lifecycle. By running idea, rigour, and claim checks in code, the system enforces novelty screening, statistical validity, execution provenance, and numerical traceability. We evaluate OmniScientist on 36 real-data cases spanning 5 discipline families, 4 families of scientific evidence, and modalities including images, signals, audio, video, 3-D structures, trajectories, tables, formulae, and graphs. The system completes the full path from raw data to a compiled manuscript in all 36 cases and achieves a mean overall paper score of 6.3 with the reference reasoning backbone. In paired comparisons against a blind variant that receives only precomputed scalar features, direct perception improves all 7 evaluation dimensions and wins 85% of head-to-head judgments. These results show that lifecycle-wide perception is essential for evidence-grounded scientific discovery and provides a practical path toward broadly capable AI scientists.

Bobo Li, Hao Fei, Tianjie Ju +2

1National University of Singapore · University of Oxford

AI Agents for Scientific DiscoveryScientific DiscoveryAutonomous Scientific DiscoveryEvidence-Grounded GenerationScientific Workflow Automation
AskPDF