Accelerating scientific discovery with Co-Scientist
By Juraj Gottweis, Wei-Hung Weng, A. Daryin, Tao Tu, Anil Palepu, Petar Sirkovic, Artiom Myaskovsky, Felix Weissenberger, Keran Rong, Ryutaro Tanno and 24 more. Nature, 2025
360 citations recorded by the source corpus.
Scientific discovery is driven by scientists generating hypotheses for complex problems that undergo rigorous experimental validation. To augment this process, we introduce Co-Scientist, a multi-agent artificial intelligence (AI) system built on Gemini for structured scientific thinking and hypothesis generation. Co-Scientist aims to help scientists discover new original knowledge. Conditioned on their research objectives and previous scientific evidence, it formulates demonstrably novel research hypotheses for experimental verification. The system’s design involves agents continuously generating, critiquing and refining hypotheses accelerated by scaling test-time compute. Key contributions include (1) a multi-agent architecture with an asynchronous task execution framework for flexible compute scaling, and (2) a tournament evolution process for self-improving hypotheses generation. Automated evaluations show continued benefits of test-time compute scaling, improving hypothesis quality over time. Although this is a general-purpose system, we focus the validation in three biomedical applications: drug repurposing; novel-target discovery1; and explaining mechanisms of antimicrobial resistance2. Specifically, Co-Scientist helped to identify new drug-repurposing candidates and synergistic combination therapies for acute myeloid leukaemia that were validated through in vitro experiments. These real-world validations demonstrate the potential of Co-Scientist to accelerate scientific discovery and usher in an era of AI-empowered scientists. Co-Scientist is an AI system for structured scientific thinking and generates research hypotheses for experimental verification.
Subfields: Information Systems and Management, Molecular Biology
View Paper: https://www.semanticscholar.org/paper/390c607723e9767a9a873ded3bc1f66808215e8e
Citations in the corpus
- AlphaEvolve: A coding agent for scientific and algorithmic discovery (2025, neutral): “However, concurrent work shows this is possible [34], and a natural step would be to link the two settings, with LLMs providing feedback on high-level ideas before transitioning to an implementation stage, for which machine feedback is available through code execution.”