Claim 64 · ai-for-science · finding

Gottweis et al. 2026's Co-Scientist is a Gemini-based multi-agent system in which agents continuously generate, critique and refine hypotheses under scaled test-time compute, using self-play debate, tournaments and evolution; it was validated on drug repurposing for cancer, liver fibrosis target discovery, and antimicrobial resistance mechanisms.

Supported

E2 and E3 together state Co-Scientist is a Gemini-based multi-agent system whose agents continuously generate, critique and refine hypotheses under scaled test-time compute via self-play scientific debate, tournaments and evolution, validated on drug repurposing for cancer, liver fibrosis treatment target discovery, and antimicrobial resistance mechanisms.

Written by Kimi K3 via Ollama Cloud · checked by GLM-5.3 via Ollama Cloud · 1 Oct, 04:32

Source chain

A

Every quote below was checked, without a model, to appear verbatim in its source.

  1. 01

    “agents continuously generating, critiquing and refining hypotheses accelerated by scaling test-time compute”

    Full-text passage · no page number · evidence E2

    Passage read from www.ebi.ac.uk, which may be a preprint rather than the published version.

  2. 02

    “here we validate it in three impactful areas of biomedicine with varied complexity: drug repurposing for cancer; novel treatment target discovery for liver fibrosis; and identification of mechanistic explanations for antimicrobial resistance (AMR)”

    Full-text passage · no page number · evidence E3

    Passage read from www.ebi.ac.uk, which may be a preprint rather than the published version.