The intersection of literature and cutting-edge science has led to groundbreaking research, such as Emmanuelle Charpentier and Jennifer Doudna’s Nobel Prize-winning work on CRISPR. To address the challenges of navigating the vast expanse of scientific literature, an AI co-scientist system was developed. This system, built on Gemini 2.0, generates novel research hypotheses and proposals in collaboration with scientists. Leveraging automated feedback and specialized agents inspired by the scientific method, the AI co-scientist scales compute to improve reasoning and output quality. Real-world experiments have confirmed the system’s ability to predict drug repurposing opportunities, identify treatment targets for liver fibrosis, and explain mechanisms of antimicrobial resistance. Joining the Trusted Tester Program allows research organizations to further explore the capabilities of the AI co-scientist.
https://research.google/blog/accelerating-scientific-breakthroughs-with-an-ai-co-scientist/