Accelerating scientific discovery with Co-Scientist
Open accessPublished version of a preprint
The DOI matches its OpenAlex record; 15 of the 15 references it cites were found in a registry or an index.
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Induction of Pluripotent Stem Cells from Adult Human Fibroblasts by Defined Factors
Takahashi, K., Tanabe, K., Ohnuki, M., Narita, M., Ichisaka, T., Tomoda, K., & Yamanaka, S. (2007) · Cell · doi:10.1016/j.cell.2007.11.019 · Cited by 20,221
Neural networks and physical systems with emergent collective computational abilities.
Hopfield, J. J. (1982) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.79.8.2554 · Cited by 19,270
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Self-citationDistilling the Knowledge in a Neural Network
Hinton, G., Vinyals, O., & Dean, J. (2015) · arXiv · doi:10.48550/arxiv.1503.02531 · Cited by 14,204
Drug repurposing: progress, challenges and recommendations
Pushpakom, S., Iorio, F., Eyers, P. A., Escott, K. J., Hopper, S., Wells, A., Doig, A., Guilliams, T., Latimer, J., McNamee, C., et al. (2019) · Nature Reviews Drug Discovery · doi:10.1038/nrd.2018.168 · Cited by 4,718
On the Opportunities and Risks of Foundation Models
Bommasani, R., Hudson, D. A., Adeli, E., Altman, R., Arora, S., von Arx, S., Bernstein, M. S., Bohg, J., Bosselut, A., Brunskill, E., et al. (2021) · arXiv · doi:10.48550/arxiv.2108.07258 · Cited by 2,676
Anil, R., Dai, A. M., Firat, O., Johnson, M., Lepikhin, D., Passos, A., Shakeri, S., Taropa, E., Bailey, P., Chen, Z., et al. (2023) · arXiv · doi:10.48550/arxiv.2305.10403 · Cited by 834
Self-citationSuperhuman AI for multiplayer poker
Brown, N., & Sandholm, T. (2019) · Science · doi:10.1126/science.aay2400 · Cited by 592
Jailbreaking Black Box Large Language Models in Twenty Queries
Chao, P., Robey, A., Dobriban, E., Hassani, H., Pappas, G. J., & Wong, E. (2023) · arXiv · doi:10.48550/arxiv.2310.08419 · Cited by 522
The risks of risk-based regulation: Insights from the environmental policy domain
Rothstein, H., Irving, P., Walden, T., & Yearsley, R. (2006) · Environment International · doi:10.1016/j.envint.2006.06.008 · Cited by 123
Research works printed but not linked: 29
- Guan, Y. et al. AI-assisted drug re-purposing for human liver fibrosis. Adv. Sci. 12, e08751 (2025). · DOI
- Penadés, J. R. et al. AI mirrors experimental science to uncover a novel mechanism of gene transfer crucial to bacterial evolution. Cell 188, 6654–6665 (2025). · DOI · Paper page
- Jinek, M. et al. A programmable dual-RNA-guided DNA endonuclease in adaptive bacterial immunity. Science 337, 816–821 (2012). · DOI · Paper page
- Hinton, G. E. & Sejnowski, T. J. in Parallel Distributed Processing: Explorations in the Microstructure of Cognition Vol. 1 (eds Feldman, J. A. et al.) 282–317 (MIT Press, 1986).
- Guo, D. et al. DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning. Nature 645, 633–638 (2025). · doi:10.1038/s41586-025-09422-z · Paper page
- Jaech, A. et al. OpenAI O1 system card. Preprint at https://arxiv.org/abs/2412.16720 (2024). · arXiv
- Gemini Team, Google. Gemini 1.5: unlocking multimodal understanding across millions of tokens of context. Preprint at https://arxiv.org/abs/2403.05530 (2024). · arXiv
- Gemma Team, Google. Gemma: open models based on gemini research and technology. Preprint at https://arxiv.org/abs/2403.08295 (2024). · arXiv
- Leslie, D. et al. ‘Frontier AI,’ power, and the public interest: who benefits, who decides? Harvard Data Sci. Rev. https://doi.org/10.1162/99608f92.4a42495c (2024). · DOI
- Chen, L. et al. Are more LLM calls all you need? Towards the scaling properties of compound AI systems. Adv. Neural Inform. Process. Syst. 37, 45767–45790 (2024). · DOI
- Gower, B. Scientific Method: a Historical and Philosophical Introduction (Routledge, 2012).
- Ringel, M. S., Scannell, J. W., Baedeker, M. & Schulze, U. Breaking Eroom’s law. Nat. Rev. Drug Discov. 19, 833–834 (2020). · DOI
- He, L. et al. Chimeric infective particles expand species boundaries in phage-inducible chromosomal island mobilization. Cell 188, 6636–6653 (2025). · DOI
- Döhner, H., Weisdorf, D. J. & Bloomfield, C. D. Acute myeloid leukemia. N. Engl. J. Med. 373, 1136–1152 (2015). · DOI · Paper page
- Guo, Q. et al. NF-κB in biology and targeted therapy: new insights and translational implications. Signal Transduc. Target. Ther. 9, 53 (2024). · DOI · Paper page
- Maiti, A. et al. Phase II trial of MEK inhibitor binimetinib (MEK162) in RAS-mutant acute myeloid leukemia. Clin. Lymphoma Myeloma Leuk. 19, 142–148 (2019). · DOI
- Philippe, C. et al. Pivotal role of the endoplasmic reticulum stress-related XBP1s/miR-22/SIRT1 axis in acute myeloid leukemia apoptosis and response to chemotherapy. Leukemia 38, 1764–1776 (2024). · DOI
- Guan, Y. et al. A human multi-lineage hepatic organoid model for liver fibrosis. Nat. Commun. 12, 6138 (2021). · DOI · Paper page
- Guan, Y. et al. Live-cell imaging of human liver fibrosis using hepatic micro-organoids. JCI Insight 10, e187099 (2024). · DOI · Paper page
- Jones, N. OpenAI’s ‘deep research’ tool: is it useful for scientists? Nature https://doi.org/10.1038/d41586-025-00377-9 (2025). · DOI
- Megat, S. et al. Integrative genetic analysis illuminates ALS heritability and identifies risk genes. Nat. Commun. 14, 342 (2023). · DOI
- Elo, A. E. The Rating of Chess Players, Past and Present (Ishi Press, 2008).
- LeCun, Y. A theoretical framework for back-propagation. In Proc. 1988 Connectionist Models Summer School Vol. 1 (eds Touretzky, D. et al.) 21–28 (Morgan Kaufmann, 1988).
- Hamilton, A. H., Kalenkova, A. & Roughan, M. The impact of intransitivity on the Elo rating system. PLoS One 20, e0338261 (2025). · DOI
- Coulom, R. Computing ‘Elo ratings’ of move patterns in the game of go. ICGA J. 30, 198–208 (2007). · DOI · Paper page
- Kovalchik, S. Extension of the Elo rating system to margin of victory. Int. J. Forecast. 36, 1329–1341 (2020). · DOI
- Khan, A. et al. Debating with more persuasive LLMs leads to more truthful answers. In Proc. 41st International Conference on Machine Learning Vol. 235 (eds Salakhutdinov, R. et al.) 23662–23733 (PMLR, 2024).
- Post, M. & Vilar, D. Fast lexically constrained decoding with dynamic beam allocation for neural machine translation. In Proc. 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Vol. 1 (Long Papers) 1314–1324 (Association for Computational Linguistics, 2018). · DOI · Paper page
- Gemini Team, Google. Gemini: a family of highly capable multimodal models. Preprint at https://arxiv.org/abs/2312.11805 (2023). · arXiv
Cited by
Why Do Multi-Agent LLM Systems Fail?
Cemri, M., Pan, M. Z., Yang, S., Agrawal, L. A., Chopra, B., Tiwari, R., Keutzer, K., Parameswaran, A., Klein, D., Ramchandran, K., et al. (2025) · arXiv · doi:10.48550/arxiv.2503.13657 · Cited by 630
Next-generation agentic AI for transforming healthcare
Karunanayake, N. (2025) · Informatics and Health · doi:10.1016/j.infoh.2025.03.001 · Cited by 165
Generative artificial intelligence in medicine
Teo, Z. L., Thirunavukarasu, A. J., Elangovan, K., Cheng, H., Moova, P., Soetikno, B., Nielsen, C., Pollreisz, A., Ting, D. S. J., Morris, R. J. T., et al. (2025) · Nature Medicine · doi:10.1038/s41591-025-03983-2 · Cited by 119
Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents
de Witt, C. S., Krawiecka, K., Krawczuk, I., Hagag, B., Anderson, W. L., Belcak, P., Bucknall, B., Cai, X., Chopra, A., Cohen, D., et al. (2025) · arXiv · doi:10.48550/arxiv.2505.02077 · Cited by 108
A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents
Huang, W.-C., Zhang, W., Liang, Y., Bei, Y., Chen, Y., Feng, T., Pan, X., Tan, Z., Wang, Y., Wei, T., et al. (2026) · arXiv · doi:10.48550/arxiv.2602.06052 · Cited by 70
Metadata
- Authors
- Gottweis, J., Weng, W., Daryin, A., Tu, T., Sirkovic, P., Myaskovsky, A., Glowaty, G., Weissenberger, F., Orlandi, A., Popovici, D., Palepu, A., Rong, K., Tanno, R., Saab, K. K., Zhang, F., Blum, J. A., Carroll, A. W., Kulkarni, K., Tomašev, N., Zverinski, D., Rendulic, I., Vedadi, E., Hasler, F., Rimanić, L., Boia, M., Budiselic, I., Feinstein, B., Bellaiche, M., Sheffer, T., Freyberg, J., Ratcliff, J., Bertolli, O., Chou, K., Hassidim, A., Gokturk, S. B., Vahdat, A., Guan, Y., Dhillon, V., Vaishnav, E. D., Lee, B., Costa, T. R. D., Penadés, J. R., Peltz, G., Matias, Y., Manyika, J., Hassabis, D., Xu, Y., Kohli, P., Pawlosky, A., Karthikesalingam, A., & Natarajan, V.
- Venue
- Nature
- Published
- 2026-05-19
- Volume
- 655
- Issue
- 8122
- Pages
- 487-496
- ISSN
- 0028-0836 (ISSN-L)
- 1476-4687
- OpenAlex
- W4416043407
- Cited by
- 110
- References
- 15
- FWCI
- 359.95
- Type
- journal article
- Language
- en
- Open access
- hybrid
- Licence
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor, 43 d)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Accelerating scientific discovery with Co-Scientist. https://app.cochat.ai/papers/10.1038/s41586-026-10644-y
- The paper
- Gottweis, J., Weng, W., Daryin, A., Tu, T., Sirkovic, P., Myaskovsky, A., Glowaty, G., Weissenberger, F., Orlandi, A., Popovici, D., Palepu, A., Rong, K., Tanno, R., Saab, K. K., Zhang, F., Blum, J. A., Carroll, A. W., Kulkarni, K., Tomašev, N., . . . Natarajan, V. (2026). Accelerating scientific discovery with Co-Scientist. Nature. https://doi.org/10.1038/s41586-026-10644-y
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.