Towards an AI co-scientist
Juraj Gottweis, Wei-Hung Weng, Alexander Daryin, Tao Tu, Anil Palepu, Petar Sirkovic, Artiom Myaskovsky, Felix Weissenberger, Keran Rong, Ryutaro Tanno, Khaled Saab, Dan Popovici, Jacob Blum, Fan Zhang, Katherine Chou, Avinatan Hassidim, Burak Gokturk, Amin Vahdat, Pushmeet Kohli, Yossi Matias, Andrew Carroll, Kavita Kulkarni
2025-02-27
Summary
This paper talks about an AI system called the AI co-scientist, which is designed to help human scientists come up with new ideas and research plans in science, especially in medicine and biology
What's the problem?
Scientists often struggle to come up with new ideas for research because there's so much information to process and it's hard to make connections across different fields. This slows down scientific progress and makes it harder to solve complex problems in medicine and biology
What's the solution?
The researchers created the AI co-scientist, which uses multiple AI agents working together to generate, debate, and improve research ideas. It's built on a powerful AI model called Gemini 2.0 and uses special techniques to process a lot of information quickly. The system was tested in three areas of medical research: finding new uses for existing drugs, discovering new targets for medicines, and understanding how bacteria evolve
Why it matters?
This matters because it could speed up scientific discoveries, especially in medicine. The AI co-scientist has already helped find potential new treatments for leukemia and liver disease, and it figured out a new way that bacteria share genes. This could lead to faster development of new medicines, better understanding of diseases, and more breakthroughs in science. It shows how AI can work alongside human scientists to solve complex problems and push the boundaries of what we know
Abstract
Scientific discovery relies on scientists generating novel hypotheses that undergo rigorous experimental validation. To augment this process, we introduce an AI co-scientist, a multi-agent system built on Gemini 2.0. The AI co-scientist is intended to help uncover new, original knowledge and to formulate demonstrably novel research hypotheses and proposals, building upon prior evidence and aligned to scientist-provided research objectives and guidance. The system's design incorporates a generate, debate, and evolve approach to hypothesis generation, inspired by the scientific method and accelerated by scaling test-time compute. Key contributions include: (1) a multi-agent architecture with an asynchronous task execution framework for flexible compute scaling; (2) a tournament evolution process for self-improving hypotheses generation. Automated evaluations show continued benefits of test-time compute, improving hypothesis quality. While general purpose, we focus development and validation in three biomedical areas: drug repurposing, novel target discovery, and explaining mechanisms of bacterial evolution and anti-microbial resistance. For drug repurposing, the system proposes candidates with promising validation findings, including candidates for acute myeloid leukemia that show tumor inhibition in vitro at clinically applicable concentrations. For novel target discovery, the AI co-scientist proposed new epigenetic targets for liver fibrosis, validated by anti-fibrotic activity and liver cell regeneration in human hepatic organoids. Finally, the AI co-scientist recapitulated unpublished experimental results via a parallel in silico discovery of a novel gene transfer mechanism in bacterial evolution. These results, detailed in separate, co-timed reports, demonstrate the potential to augment biomedical and scientific discovery and usher an era of AI empowered scientists.