ArticleNature2026
Accelerating scientific discovery with Co-Scientist.
Article in Nature, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 24 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
24 citing papers in PubMed.
- Article
- Big Data and Artificial Intelligence in Cancer Drug Discovery: Promise, Challenges, and Emerging Opportunities.Cancers · 2026Review
- Artificial Intelligence in Medical Writing: A Practical and Ethical Framework for Surgical Research and Publication.World journal of surgery · 2026Review
- Article
- ELISA (Embedding-Linked Interactive Single-cell Agent): an interpretable hybrid generative Artificial Intelligence agent for expression-grounded discovery in single-cell genomics.Briefings in bioinformatics · 2026Article
- The future of AI-assisted science is both fast and slow.Nature human behaviour · 2026Article
- Self-Driving Scanning Probe Microscopy: From Acceleration to Discovery and Manipulation.Accounts of chemical research · 2026Article
- Why do AI projects fail in drug development and pharma? Insights from multi-year Pistoia Alliance studies.Journal of computer-aided molecular design · 2026Article
- XunZi, an AI biologist, reveals disease-modifying targets.Nature biomedical engineering · 2026Article
- Agentic artificial intelligence in medicine and biomedical research: A primer and framework for clinicians and researchers.JAAD international · 2026Article
- From Chatbots to Co-Scientists: The Impact of Knowledge-Generating AI (AI 4.0) on Healthcare and Research.Advanced science (Weinheim, Baden-Wurttemberg, Germany) · 2026Article
- Graph in Graph (GiG): A novel graph AI framework for integrating and interpreting medical and omics data.bioRxiv : the preprint server for biology · 2026Article
- MechAInistic: A Reviewer-Supervised Multi-Agent LLM System for Auditable Mechanistic Drug-Hypothesis Generation.bioRxiv : the preprint server for biology · 2026Article
- CuGen: A GPU-accelerated framework for large-scale genomics.medRxiv : the preprint server for health sciences · 2026Article
- Why biology must prioritize data reanalysis in the era of artificial intelligence.PLoS biology · 2026Article
- Article
- Empowering biomedical evidence exploration and synthesis with deep knowledge graph research.Nature machine intelligence · 2026Article
- Practical Use of Advanced AI Frameworks on Real-Life Scientific Problems: Three Case Studies.bioRxiv : the preprint server for biology · 2026Article
- Evaluating agentic AI for biological discovery in autonomous and copilot settings.bioRxiv : the preprint server for biology · 2026Article
- Ontology-constrained multi-LLM scoring of hypothesis support in the predictive processing literature.Research square · 2026Article
Corrections and comments
- Update of
Authors and funding
51 authors.
Funding
No grant is acknowledged in the PubMed record.
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
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.