Olympiad-level formal mathematical reasoning with reinforcement learning

Thomas Hubert, Rishi Mehta, Laurent Sartran, Miklós Z. Horváth, Goran Žužić, Eric Wieser, Aja Huang, Julian Schrittwieser, Yannick Schroecker, Hussain Masoom, Ottavia Bertolli, Tom Zahavy, Amol Mandhane, Jessica Yung, Iuliya Beloshapka, Borja Ibarz, Vivek Veeriah, Lei Yu, Oliver Nash, Paul Lezeau, Salvatore Mercuri, Calle Sönne, Bhavik Mehta, Alex Davies, Daniel Zheng, Fabian Pedregosa, Yin Li, Ingrid von Glehn, Mark Rowland, Samuel Albanie, Ameya Velingker, Simon Schmitt, Edward Lockhart, Edward Hughes, Henryk Michalewski, Nicolas Sonnerat, Demis Hassabis, Pushmeet Kohli, David Silver

Open source

DOI
10.1038/s41586-025-09833-y
Published
2025-11-12
Container
Nature
Publisher
Springer Science and Business Media LLC
Open access
unknown

Credibility signals

uncertain Score 64/100 under policy 1.0.0. This is a metadata assessment, not a judgment of the paper's conclusions.

Show all credibility signals

Cite this work

BibTeX

@article{allodium:10.1038/s41586-025-09833-y,
  title = {Olympiad-level formal mathematical reasoning with reinforcement learning},
  author = {Thomas Hubert and Rishi Mehta and Laurent Sartran and Miklós Z. Horváth and Goran Žužić and Eric Wieser and Aja Huang and Julian Schrittwieser and Yannick Schroecker and Hussain Masoom and Ottavia Bertolli and Tom Zahavy and Amol Mandhane and Jessica Yung and Iuliya Beloshapka and Borja Ibarz and Vivek Veeriah and Lei Yu and Oliver Nash and Paul Lezeau and Salvatore Mercuri and Calle Sönne and Bhavik Mehta and Alex Davies and Daniel Zheng and Fabian Pedregosa and Yin Li and Ingrid von Glehn and Mark Rowland and Samuel Albanie and Ameya Velingker and Simon Schmitt and Edward Lockhart and Edward Hughes and Henryk Michalewski and Nicolas Sonnerat and Demis Hassabis and Pushmeet Kohli and David Silver},
  year = {2025},
  journal = {Nature},
  doi = {10.1038/s41586-025-09833-y},
  url = {https://doi.org/10.1038/s41586-025-09833-y}
}

RIS

TY  - JOUR
TI  - Olympiad-level formal mathematical reasoning with reinforcement learning
AU  - Thomas Hubert
AU  - Rishi Mehta
AU  - Laurent Sartran
AU  - Miklós Z. Horváth
AU  - Goran Žužić
AU  - Eric Wieser
AU  - Aja Huang
AU  - Julian Schrittwieser
AU  - Yannick Schroecker
AU  - Hussain Masoom
AU  - Ottavia Bertolli
AU  - Tom Zahavy
AU  - Amol Mandhane
AU  - Jessica Yung
AU  - Iuliya Beloshapka
AU  - Borja Ibarz
AU  - Vivek Veeriah
AU  - Lei Yu
AU  - Oliver Nash
AU  - Paul Lezeau
AU  - Salvatore Mercuri
AU  - Calle Sönne
AU  - Bhavik Mehta
AU  - Alex Davies
AU  - Daniel Zheng
AU  - Fabian Pedregosa
AU  - Yin Li
AU  - Ingrid von Glehn
AU  - Mark Rowland
AU  - Samuel Albanie
AU  - Ameya Velingker
AU  - Simon Schmitt
AU  - Edward Lockhart
AU  - Edward Hughes
AU  - Henryk Michalewski
AU  - Nicolas Sonnerat
AU  - Demis Hassabis
AU  - Pushmeet Kohli
AU  - David Silver
PY  - 2025
JO  - Nature
DO  - 10.1038/s41586-025-09833-y
UR  - https://doi.org/10.1038/s41586-025-09833-y
ER  -

APA

Hubert, T., Mehta, R., Sartran, L., Horváth, M. Z., Žužić, G., Wieser, E., Huang, A., Schrittwieser, J., Schroecker, Y., Masoom, H., Bertolli, O., Zahavy, T., Mandhane, A., Yung, J., Beloshapka, I., Ibarz, B., Veeriah, V., Yu, L., Nash, O., Lezeau, P., Mercuri, S., Sönne, C., Mehta, B., Davies, A., Zheng, D., Pedregosa, F., Li, Y., Glehn, I. V., Rowland, M., Albanie, S., Velingker, A., Schmitt, S., Lockhart, E., Hughes, E., Michalewski, H., Sonnerat, N., Hassabis, D., Kohli, P., & Silver, D. (2025). Olympiad-level formal mathematical reasoning with reinforcement learning. Nature. https://doi.org/10.1038/s41586-025-09833-y

Source records