Google's Co-Scientist Expands to Multi-Disciplinary Closed-Loop Discovery
vivnat · x · 2026-09-01
Google DeepMind highlighted progress with Co-Scientist, extending it from biomedical hypothesis generation to execution-grounded closed-loop discovery across multiple scientific disciplines. Three new preprints showcase applications in math and cancer biology: In math, the AI collaborated iteratively with experts to tackle the Chowla sets problem; in cancer biology, Genentech introduced PerturbME, a sample-efficient method.
Related event: Google's Co-Scientist Achieves Closed-Loop Discovery Across Sciences(2 posts)→
More from Research
- Interpretability debate: one interpretable polysemantic neuron doesn't prove all are — aran_nayebi · 2026-10-16
- Optuna creator Akiba: when 2 hyperparameters cost $20M, what's left for BO/HPO — Stefania_druga · 2026-10-16
- AI will be superhuman at science regardless, and Europe can't opt out — teortaxesTex · 2026-10-16
- SERO augments long-horizon agentic RL with executable oracle continuations — Shanghai-AI-Laboratory · 2026-10-16
- Tsinghua and Amap propose OmniVerifier-C1, a graded verifier beating binary judges — Bowei Liu · 2026-10-16
- Alibaba open-sources MAI-Gym, an all-in-one GUI agent eval and RL training platform — Tongyi-MAI · 2026-10-16