MétaCan
Menu
Back to cohort
Record W4416437085 · doi:10.48550/arxiv.2511.02824

Kosmos: An AI Scientist for Autonomous Discovery

2025· preprint· W4416437085 on OpenAlexfundno aff
Ludovico Mitchener, Angela Yiu, Benjamin Chang, Mathieu Bourdenx, Tyler Nadolski, Arvis Sulovari, Eric C. Landsness, Dániel L. Barabási, Siddharth Narayanan, Shriya Reddy, Martha Foiani, Leah P. Shriver, Fang Cao, Asmamaw T. Wassie, Jon M. Laurent, Edwin Melville-Green, Albert Bou, Sladjana Zagorac, Miranda E. Orr, Kevin J. Zwezdaryk, Ali Essa Ghareeb, Bruna Gomes, Euan A. Ashley, Karen Duff, Tonio Buonassisi, Tom Rainforth, Randall J. Bateman, Michael Skarlinski, Samuel G. Rodriques, Michaela M. Hinks, Andrew Dickson White

Bibliographic record

VenueArXiv.org · 2025
Typepreprint
Language
FieldBiochemistry, Genetics and Molecular Biology
TopicBiomedical Text Mining and Ontologies
Canadian institutionsnot available
FundersNational Institutes of HealthEngineering and Physical Sciences Research CouncilUK Dementia Research InstituteMedical Research CouncilCure Alzheimer's FundCanadian Institute for Advanced ResearchToyota Research Institute
KeywordsLimitingCode (set theory)Reading (process)Scientific discoverySource code

Abstract

fetched live from OpenAlex

Data-driven scientific discovery requires iterative cycles of literature search, hypothesis generation, and data analysis. Substantial progress has been made towards AI agents that can automate scientific research, but all such agents remain limited in the number of actions they can take before losing coherence, thus limiting the depth of their findings. Here we present Kosmos, an AI scientist that automates data-driven discovery. Given an open-ended objective and a dataset, Kosmos runs for up to 12 hours performing cycles of parallel data analysis, literature search, and hypothesis generation before synthesizing discoveries into scientific reports. Unlike prior systems, Kosmos uses a structured world model to share information between a data analysis agent and a literature search agent. The world model enables Kosmos to coherently pursue the specified objective over 200 agent rollouts, collectively executing an average of 42,000 lines of code and reading 1,500 papers per run. Kosmos cites all statements in its reports with code or primary literature, ensuring its reasoning is traceable. Independent scientists found 79.4% of statements in Kosmos reports to be accurate, and collaborators reported that a single 20-cycle Kosmos run performed the equivalent of 6 months of their own research time on average. Furthermore, collaborators reported that the number of valuable scientific findings generated scales linearly with Kosmos cycles (tested up to 20 cycles). We highlight seven discoveries made by Kosmos that span metabolomics, materials science, neuroscience, and statistical genetics. Three discoveries independently reproduce findings from preprinted or unpublished manuscripts that were not accessed by Kosmos at runtime, while four make novel contributions to the scientific literature.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.007
metaresearch head score (Gemma)0.028
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Software · Consensus signal: none
Teacher disagreement score0.013
Threshold uncertainty score0.043

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0070.028
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.002
Bibliometrics0.0020.001
Science and technology studies0.0010.002
Scholarly communication0.0040.007
Open science0.0040.007
Research integrity0.0020.003
Insufficient payload (model declined to judge)0.0130.008

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.037
GPT teacher head0.333
Teacher spread0.296 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreSoftware

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations7
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueArXiv.orgSame topicBiomedical Text Mining and OntologiesFrench-language works237,207