Nature

The AI Scientist is the first fully autonomous AI system to generate a paper that passed peer review (ICLR 2025 ICBINB workshop). It creates research ideas, writes code, runs experiments, analyses data, writes manuscripts, and performs peer review — all end-to-end. Template-free mode uses agentic tree search for open-ended scientific exploration. An automated reviewer achieves balanced accuracy comparable to human reviewers (69%). Paper quality scales with foundation model capability and test-time compute.

The automation of science is a long-standing ambition in artificial intelligence research. Although the community has made substantial progress in automating individual components of the scientific process, a system that autonomously navigates the entire research life cycle from conception to publication has remained out of reach. Here we present a pipeline for automating the entire scientific process end to end. We present The AI Scientist, which creates research ideas, writes code, runs experiments, plots and analyses data, writes the entire scientific manuscript, and performs its own peer review. Its ideas, execution and presentation are of sufficient quality that the manuscript generated by this AI system passed the first round of peer review for a workshop of a top-tier machine learning conference.

MIRA is an autonomous AI agent powered by GPT-4o (T=0.01) with o1-preview for structured reasoning, operating within a sandboxed HL7 FHIR-based EHR environment. It navigates 85,000+ clinical decision options across 8 emergency department diagnoses, using 11 FHIR-compliant tools (PatientHistory, PhysicalExam, Lab/Urine/Microbiology/Radiology requests, Medication/Procedure ordering, Plan, Admission). Evaluated on 574 real MIMIC-IV patient cases, MIRA outperformed two independent physician cohorts in diagnostic accuracy, guideline-concordant treatment, medication safety, and appropriate admission decisions. All tool parameter validity is enforced through token masking, making hallucination of non-existent options programmatically impossible.

Large language models (LLMs) show great potential for clinical decision-making, yet most applications remain narrow, task-specific chat tools rather than systems integrated into clinical workflows. However, building physician copilots will require models that operate within the electronic health record (EHR), with governed access to patient data and the ability to initiate permitted EHR actions within defined safety constraints. Here we show that MIRA (Medical Intelligence for Reasoning and Action), an autonomous artificial intelligence agent operating in a sandboxed EHR environment, can navigate a large clinical action space to obtain patient histories; order and interpret laboratory, imaging and microbiology tests; generate differential diagnoses; and formulate treatment plans such as prescribing medications, scheduling surgical procedures and planning admissions. In simulations on real patient cases spanning multiple diagnoses, MIRA outperformed physicians in diagnostic accuracy and made guideline-concordant, medication-safe and appropriate admission decisions.

ExAC v1.0 published in Nature (Lek et al., 2016), analyzing exome data from 60,706 individuals. This landmark resource cataloged over 10 million variants, established allele frequency filters for clinical variant interpretation, and demonstrated that most genes are extremely tolerant of loss-of-function variation. The ExAC browser became the de facto standard for variant annotation.

FinnGen R7 data freeze of 224,737 participants analyzed across 1,932 disease endpoints. Identified 30 new low-frequency variant associations enriched in Finland, and 2,733 genome-wide significant associations through phenome-wide scanning. Published in Nature (Kurki et al., 2023).