External pipelines · RISE project catalogue
AI Co-Scientist (Google DeepMind)
Google's closed multi-agent research partner (announced Feb 2025, published in Nature 2026-05-19) that generates, debates, and evolves novel research hypotheses. Built on Gemini, it orchestrates six specialized agents — Generation, Reflection, Ranking, Proximity, Evolution, Meta-review — under a Supervisor, using Elo-based tournaments and simulated scientific debate to surface and refine ideas. It sits in the upstream *ideation* layer: it proposes hypotheses and experiments but does not run experiments, analyze data, or draft papers.
Where it sits
left: what it builds on · right: what builds on it · pale: exampleContributed by Google DeepMind, Google Research
How studies reach it
No published study reaches it yet.
Disciplines it reaches
No study reaches it yet.
Solid: published studies. Light: examples.
Computed from the records on this site: what each study, template and specialist names as used, which study extends which, and who contributed what. 0 studies in total.
What it does
The most externally validated hypothesis-generation system on the landscape: peer-reviewed in Nature, with wet-lab confirmation of AI-proposed leads in AML drug repurposing, liver-fibrosis reversal, and antimicrobial-resistance gene transfer, and active use by infectious-disease, aging, and ALS research teams across 100+ institutions. RISE separately catalogs the open-source reimplementation open-coscientist; this entry is the closed, first-party system whose design that project reverse-engineers.
- Focus
- ideation
- Inputs
- research-goal
- Outputs
- ranked-hypotheses, research-proposals, research-overview
- Architecture
- multi-agent, tool-use, rag-knowledge-base, iterative-loop, debate-consensus
- Maintained by
- Google DeepMind; Google Research
- Started
- 2025
Description
Data model- Discipline
- General
- Method family
- not specified
- Design
- not specified
- Research stage
- Literature discoveryLiterature synthesisHypothesesResearch design
- Contributors
- Google DeepMind; Google Research
- Usage
- not used in published research yet
- Source
- RISE project catalogue · projects/landscape · @4c17bae
- Record
- pipeline:google-co-scientist · JSON
Solid tags are declared by the source or mapped from its terms; dashed tags are inferred by a published rule. Hover a tag for its provenance.
Bring it into the standard
A pipeline built outside E2ER can meet the standard by describing its steps as a template, attaching the floor of checks and publishing evaluation records. Its authors keep ownership and credit.