---
id: "2025-02-19-google-ai-co-scientist"
url: "https://postcutoff.com/e/2025-02-19-google-ai-co-scientist/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2025-02-19"
date_precision: day
category: science
importance: 4
confidence: high
status: [Result confirmed]
verification: Peer-reviewed
sources: 5
editor: human editor
human_review: null
version: "2026-10-04"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2025-02-19-google-ai-co-scientist/

# Google's AI co-scientist independently reproduces an unpublished superbug discovery in 48 hours

Google's Gemini 2.0–based multi-agent 'AI co-scientist' (announced 19 Feb 2025) generated hypotheses that were validated in the lab. It proposed AML drug-repurposing candidates, and liver-fibrosis drugs active in human organoids. Its top-ranked hypothesis for how cf-PICI genetic elements spread between bacteria matched Imperial College's unpublished, experimentally confirmed finding. The system was published in Nature on 19 May 2026.

## Key facts
- Agents for generation, reflection, ranking (tournament), evolution and meta-review on Gemini 2.0
- cf-PICI: 5 ranked hypotheses in 48 hours; the top one (hijacking tails from diverse phages) matched José Penadés's unpublished result; both papers later in Cell (Sep 2025)
- Liver fibrosis: 2 of the co-scientist's recommended epigenetic drugs were anti-fibrotic in human hepatic organoids (vorinostat reduced TGFβ-induced chromatin changes by 91%)
- AML: repurposing candidates inhibited tumour viability in cell lines
- Caveats: evaluation not blind or pre-registered; Google staff co-authors; 'decade-long mystery solved in 2 days' is press framing

## What happened

Google built a multi-agent system that debates and ranks research hypotheses. Partner labs tested its suggestions, and one matched an unpublished result the humans had spent years on.

## Why it matters

It was the most-cited early example of an LLM system generating a correct, non-obvious scientific hypothesis. At Google I/O 2026 it became part of the "Gemini for Science" product.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): in its training data
- Claude Opus 5.5 (training cutoff June 2026): in its training data
- Gemini 4 Hydrogen (training cutoff March 2026): in its training data
- Grok 4.7 (training cutoff May 2026): in its training data

## Sources

1. [Co-Scientist paper (Nature, 2026)](https://www.nature.com/articles/s41586-026-10644-y) (nature.com, paper)
2. [Cell: AI co-scientist and the cf-PICI mechanism](https://www.cell.com/cell/fulltext/S0092-8674(25)00973-0) (cell.com, paper)
3. [bioRxiv: cf-PICI hypothesis generated by AI co-scientist](https://www.biorxiv.org/content/10.1101/2025.02.19.639094v1.full) (biorxiv.org, paper)
4. [Advanced Science: AI-assisted liver fibrosis drug repurposing](https://advanced.onlinelibrary.wiley.com/doi/full/10.1002/advs.202508751) (advanced.onlinelibrary.wiley.com, paper)
5. [HPCwire: Google unveils AI scientist](https://www.hpcwire.com/2025/02/26/google-unveils-ai-scientist-that-could-transform-research/) (hpcwire.com, press)

## Changes

- 2026-09-29: Linked the I/O 2026 'Gemini for Science' product entry (Co-Scientist became a Labs tool and enterprise preview)
- 2026-09-29 (filed): Created

## Related

- 2026-05-19: [Google launches 'Gemini for Science' at I/O 2026](https://postcutoff.com/e/2026-05-19-google-gemini-for-science/index.md)
- 2025-11-05: [Edison Scientific's Kosmos AI scientist claims six months of research per run](https://postcutoff.com/e/2025-11-05-kosmos-ai-scientist/index.md)
- 2025-05-20: [FutureHouse's Robin multi-agent system proposes ripasudil as a new treatment candidate for dry AMD](https://postcutoff.com/e/2025-05-20-futurehouse-robin-ripasudil/index.md)