Biology
Catalog entries using this tag (links open the entry card on its page):
Entries
Robin
PUBMED_LINK
FULL NAME
Robin - A Multi-Agent System for Automating Scientific Discovery
DESCRIPTION
Robin is the first multi-agent system capable of fully automating both hypothesis generation and data analysis for experimental biology. By integrating literature search agents with data analysis agents, Robin can generate testable hypotheses from literature and design experiments to validate them, automating the entire scientific discovery cycle for biological research.
TITLE
A multi-agent system for automating scientific discovery.
Main citation
Ghareeb AE, Chang B, Mitchener L, Yiu A, Szostkiewicz CJ, Shved D, Gyimesi GJ, Laurent JM, Wright SM, Razzak MT, White AD, Finnemann SC, Hinks MM, Rodriques SG. (2026) A multi-agent system for automating scientific discovery. Nature. doi:10.1038/s41586-026-10652-y. PMID 42156546
ABSTRACT
Scientific discovery is driven by the iterative process of observation, hypothesis generation, experimentation, and data analysis. Despite recent advancements in applying artificial intelligence to biology, no system has yet automated all these stages. Here, we introduce Robin, the first multi-agent system capable of fully automating both hypothesis generation and data analysis for experimental biology. By integrating literature search agents with data analysis agents, Robin can generate testable hypotheses from literature and design experiments to validate them.
DOI
10.1038/s41586-026-10652-y