Google DeepMind's AI Co-Scientist now runs lab equipment and writes papers
This digest was compiled by AI from multiple sources — links to the originals are below.
Google DeepMind has expanded its Co-Scientist system into a lab-integrated research partner that plans experiments, controls equipment, and writes scientific papers. The system delivered experimentally validated results across materials science, biology, and computer science. The closed-loop workflow derives hypotheses, creates experimental plans, analyzes results, and generates manuscripts.
Key Facts
- Co-Scientist found a safer synthesis pathway for a 2D material previously produced mainly through hazardous etching.
- Three semiconductor thin films were synthesized on the first try using Gemini 3 Deep Think for direct equipment control.
- In biology, Co-Scientist's image analysis pipeline matched unpublished lab results for three out of four shape features in E. coli colonies.
- The system completed 25 rounds of human refinement to produce layered structures resembling the target material, but atomic structure confirmation is still pending.
Closed-Loop Research Workflow
Co-Scientist now derives hypotheses from a research question, creates experimental plans, programs, or machine-readable lab protocols, analyzes results, and generates scientific manuscripts. Verification modules cross-check numerical claims in the text against execution logs of generated code to reduce fabricated results. Google first introduced Co-Scientist in February 2025 based on Gemini 2.0, with shortcomings in fact-checking and literature review. The expanded system was validated across three disciplines with increasing autonomy: materials science, biology, and computer science.
Materials Science Validation
For material synthesis, researchers paired Co-Scientist with a semi-automated high-temperature furnace. The system generated complete growth recipes tailored to the lab's equipment and found a safer pathway for a sought-after 2D material. After 25 rounds with human refinement, the team produced layered structures whose properties resemble the target material, but definitive confirmation of the atomic structure is still pending. In a second experiment, three semiconductor thin films were synthesized on the first try. Co-Scientist used Gemini 3 Deep Think for direct equipment control, cutting recipe development from days down to minutes. Humans still had to load samples and precursor materials manually, and the fast mode produced smaller, less uniform crystals than carefully optimized recipes would.
Biology and Computer Science
In biology, Co-Scientist autonomously built an image analysis pipeline that predicts which patterns genetically engineered E. coli colonies form at different chemical concentrations. Predictions generated with Gemini 3 Pro Image matched unpublished lab results for three out of four shape features. The researchers acknowledge the system only reasons between known conditions and cannot predict behavior in entirely new systems. In computer science, Co-Scientist worked entirely on its own to develop AI architecture.
1 source
Google DeepMind's AI Co-Scientist now runs lab equipment and writes papers
