Reproduce “BioResearcher: Scenario-Guided Multi-Agent for Translational Medicine” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Remigiusz Kinas, Joanna Krawczyk, Rafał Powalski, Przemysław Pietrzak, Agnieszka Kowalewska, Krzysztof Kolmus, Maciej Sypetkowski, Łukasz Smoliński and 1 more
BioResearcher turns translational-medicine questions into planned, evidence-linked workflows. It normalizes names, delegates retrieval and analysis to specialized agents, and reconciles sourced claims into a dossier. On a 30-query expert-curated biomarker benchmark, it achieved a 74.7% positive hit rate and a 96.8% negative clear rate, outperforming CellType on both measures; these results are limited to this benchmark, not clinical validation.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.