Give scientists a tireless research partner that reads the literature and proposes new, testable hypotheses, so labs spend their experiments on the most promising ideas.
Published in Nature (May 2026); opening to researchers through Gemini for Science.
Updated 28 May 2026Checked 11 Oct0 updates this week
A researcher writes a goal in plain language; a supervisor agent splits the work among specialist agents.
One agent drafts ideas from the literature; another critiques them; a third pits them against each other in debates.
Hypotheses play pairwise matches and earn chess-style Elo ratings; the best are evolved and refined.
Top ideas go to the scientist with reasoning attached; labs then test them, as in the leukemia and liver work.
| Spec | AI co-scientist |
|---|---|
| Specialised agents | 6 plus a supervisorR (reported) |
| Base model | Gemini (2.0 at launch)R (reported) |
| Idea ranking | Elo tournament between hypothesesR (reported) |
R reported by the company
Google DeepMind
Gemini, AlphaFold, Genie, Veo, TPU chips
Google DeepMind is Alphabet's AI lab, formed in 2023 from DeepMind and Google Brain. It builds the Gemini models and leads in AI for science. AlphaFold won a share of the 2024 Nobel Prize in Chemistry.
