Abstract
AI agents promise to empower biomedical discovery, but realizing this promise requires the ability to complete transparent, long-horizon analyses using tools. Agents must make intermediate decisions explicit, and validate each decision and output against data and tool constraints as the analysis unfolds. We present Medea, an AI agent that takes an omics objective and executes a transparent multi-step analysis using tools. Medea comprises four modules: research planning with context and integrity verification, code execution with pre- and post-run checks, literature reasoning with evidence-strength assessment, and a consensus stage that reconciles evidence across datasets, tools, and literature. Medea uses 20 tools spanning single-cell and bulk transcriptomic datasets, cancer vulnerability maps, pathway knowledge bases, and machine learning models. We evaluate Medea across 5,679 analyses in three open-ended domains: target identification across five diseases and cell type contexts (2,400 analyses), synthetic lethality reasoning in seven cell lines (2,385 analyses), and immunotherapy response prediction in bladder cancer (894 patient analyses). In evaluations that vary large language models, tool sets, omics objectives, and agentic modules, Medea improves the performance of existing approaches by up to 46% for target identification, 22% for synthetic lethality, and 24% for immunotherapy response prediction, while maintaining low failure rates and calibrated abstention. Medea shows that verification-aware AI agents improve performance by producing transparent analyses, not simply more efficient workflows.