Reproduce “El Agente Fármaco: A Scalable AI Scientist for Drug Discovery” 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
Marcel Müller, Mohammad Ghazi Vakili, Yoshihiro Ogura, Ella Ashoori, Shimeng Wang, Alessandro S. Nascimento, Eddie Calleja, Yutong Zhao and 8 more
Fármaco lets researchers screen collections of molecules by storing molecules, calculations, and provenance in a database, then running workflows on saved groups and retrieving selected evidence for the next decision. Across 22 tasks, it had the highest observed mean judge score, 8.67, and lower median token use and peak context than comparison systems. Score intervals overlapped; plain tool calls were cheaper and faster.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.