Accelerating scientific discovery with Co-Scientist

J Juraj Gottweis W Wei-Hung Weng A Alexander Daryin T Tao Tu P Petar Sirkovic A Artiom Myaskovsky G Grzegorz Glowaty F Felix Weissenberger A Alessio Orlandi D Dan Popovici A Anil Palepu K Keran Rong R Ryutaro Tanno K Khaled Saab F Fan Zhang J Jacob Blum A Andrew Carroll K Kavita Kulkarni N Nenad Tomašev D Dina Zverinski I Ivor Rendulic E Elahe Vedadi F Florian Hasler L Luka Rimanic M Marina Boia I Ivan Budiselic B Ben Feinstein M Mathias Bellaiche T Tom Sheffer J Jan Freyberg J Jeremy Ratcliff O Ottavia Bertolli K Katherine Chou A Avinatan Hassidim B Burak Gokturk A Amin Vahdat Y Yuan Guan V Vikram Dhillon E Eeshit Dhaval Vaishnav B Byron Lee T Tiago R. D. Costa J José R. Penadés G Gary Peltz Y Yossi Matias J James Manyika D Demis Hassabis Y Yunhan Xu P Pushmeet Kohli A Annalisa Pawlosky A Alan Karthikesalingam V Vivek Natarajan

Abstract

Abstract Scientific discovery is driven by scientists generating hypotheses for complex problems that undergo rigorous experimental validation. To augment this process, we introduce Co-Scientist, a multi-agent artificial intelligence (AI) system built on Gemini for structured scientific thinking and hypothesis generation. Co-Scientist aims to help scientists discover new original knowledge. Conditioned on their research objectives and previous scientific evidence, it formulates demonstrably novel research hypotheses for experimental verification. The system’s design involves agents continuously generating, critiquing and refining hypotheses accelerated by scaling test-time compute. Key contributions include (1) a multi-agent architecture with an asynchronous task execution framework for flexible compute scaling, and (2) a tournament evolution process for self-improving hypotheses generation. Automated evaluations show continued benefits of test-time compute scaling, improving hypothesis quality over time. Although this is a general-purpose system, we focus the validation in three biomedical applications: drug repurposing; novel-target discovery 1 ; and explaining mechanisms of antimicrobial resistance 2 . Specifically, Co-Scientist helped to identify new drug-repurposing candidates and synergistic combination therapies for acute myeloid leukaemia that were validated through in vitro experiments. These real-world validations demonstrate the potential of Co-Scientist to accelerate scientific discovery and usher in an era of AI-empowered scientists.

Article Details

Journal Nature
Volume / Issue Vol. 655, Issue 8122
Published July 09, 2026
Pages 487-496
ISSN 0028-0836
Publisher Nature Portfolio

Journal Info

Nature

Nature Portfolio

ISSN: 0028-0836 Health Sciences

Authors (51)

J

Juraj Gottweis

W

Wei-Hung Weng

A

Alexander Daryin

T

Tao Tu

P

Petar Sirkovic

A

Artiom Myaskovsky

G

Grzegorz Glowaty

F

Felix Weissenberger

A

Alessio Orlandi

D

Dan Popovici

A

Anil Palepu

K

Keran Rong

R

Ryutaro Tanno

K

Khaled Saab

F

Fan Zhang

J

Jacob Blum

A

Andrew Carroll

K

Kavita Kulkarni

N

Nenad Tomašev

D

Dina Zverinski

I

Ivor Rendulic

E

Elahe Vedadi

F

Florian Hasler

L

Luka Rimanic

M

Marina Boia

I

Ivan Budiselic

B

Ben Feinstein

M

Mathias Bellaiche

T

Tom Sheffer

J

Jan Freyberg

J

Jeremy Ratcliff

O

Ottavia Bertolli

K

Katherine Chou

A

Avinatan Hassidim

B

Burak Gokturk

A

Amin Vahdat

Y

Yuan Guan

V

Vikram Dhillon

E

Eeshit Dhaval Vaishnav

B

Byron Lee

T

Tiago R. D. Costa

J

José R. Penadés

G

Gary Peltz

Y

Yossi Matias

J

James Manyika

D

Demis Hassabis

Y

Yunhan Xu

P

Pushmeet Kohli

A

Annalisa Pawlosky

A

Alan Karthikesalingam

V

Vivek Natarajan