Journal article · 2026 · Open access

Mathematical discovery and exploration can be done at scale

Bogdan Georgiev, Javier Gómez-Serrano, Terence Tao, Adam Zsolt Wagner

Proceedings of the National Academy of Sciences, 123(40), e2536158123 · Published 30 September 2026 · DOI 10.1073/pnas.2536158123

Open full textCite this paper

In brief

“Mathematical discovery and exploration can be done at scale” is a 2026 journal article by Bogdan Georgiev and 3 co-authors, published in Proceedings of the National Academy of Sciences. OpenAlex counts 161 citations as of 17 November 2026, which puts it in the top 1% of works published in 2026 by citations. It is open access under a CC BY-NC-ND licence: the full text is free to read at Proceedings of the National Academy of Sciences.

Citations
161
Most cited in
2026 (147)
Field-weighted impact
204.53
References
220
Authors
4

Abstract

AlphaEvolve, introduced in A. Novikov et al . [“AlphaEvolve: A coding agent for scientific and algorithmic discovery” (Tech. Rep., Google DeepMind, 2025).], is a generic evolutionary coding agent that combines large language models (LLMs) with automated evaluation in a loop that proposes, tests, and refines algorithmic solutions. Here we showcase AlphaEvolve as a tool for autonomously discovering novel mathematical constructions and making progress on long-standing open problems. On 67 problems spanning mathematical analysis, combinatorics, geometry, and number theory, the system rediscovered the best known solutions in most cases and improved on them in several. In some instances, it also generalized results for finitely many input values into a formula valid for all inputs. Furthermore, we combine this methodology with Deep Think [Google DeepMind, Advanced Version of Gemini with Deep Think Officially Achieves Gold-Medal Standard at the International Mathematical Olympiad (Google DeepMind Blog, 2025).] and AlphaProof [Google DeepMind, AI Achieves Silver-Medal Standard Solving International Mathematical Olympiad Problems (Google DeepMind Blog, 2024).] in a broader framework where the additional proof assistants and reasoning systems provide automated proof generation and further mathematical insights. These results demonstrate that LLM-guided evolutionary search can autonomously discover mathematical constructions that complement human intuition, at times matching or improving the best known results, and point to new modes of interaction between mathematicians and AI systems. AlphaEvolve explores vast search spaces to solve complex optimization problems at scale, often with significantly reduced preparation and computation time.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Georgiev, B., Gómez-Serrano, J., Tao, T., & Wagner, A. Z. (2026). Mathematical discovery and exploration can be done at scale. Proceedings of the National Academy of Sciences, 123(40), e2536158123. https://doi.org/10.1073/pnas.2536158123

MLA 9

Georgiev, Bogdan, et al. “Mathematical discovery and exploration can be done at scale.” Proceedings of the National Academy of Sciences, vol. 123, no. 40, 2026, p. e2536158123. https://doi.org/10.1073/pnas.2536158123.

Chicago

Georgiev, Bogdan, Javier Gómez-Serrano, Terence Tao, and Adam Zsolt Wagner. 2026. “Mathematical discovery and exploration can be done at scale.” Proceedings of the National Academy of Sciences 123 (40): e2536158123. https://doi.org/10.1073/pnas.2536158123.

Harvard

Georgiev, B. et al. (2026) ‘Mathematical discovery and exploration can be done at scale’, Proceedings of the National Academy of Sciences, 123(40), p. e2536158123. doi:10.1073/pnas.2536158123.

IEEE

B. Georgiev, J. Gómez-Serrano, T. Tao, and A. Z. Wagner, “Mathematical discovery and exploration can be done at scale,” Proceedings of the National Academy of Sciences, vol. 123, no. 40, p. e2536158123, 2026, doi: 10.1073/pnas.2536158123.

BibTeX

@article{georgiev2026mathematical,
  title     = {{Mathematical discovery and exploration can be done at scale}},
  author    = {Georgiev, Bogdan and Gómez-Serrano, Javier and Tao, Terence and Wagner, Adam Zsolt},
  journal   = {Proceedings of the National Academy of Sciences},
  year      = {2026},
  volume    = {123},
  number    = {40},
  pages     = {e2536158123},
  doi       = {10.1073/pnas.2536158123},
  url       = {https://doi.org/10.1073/pnas.2536158123}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Computer Science › Artificial Intelligence › Evolutionary Algorithms and Applications

  • large language models
  • open problems in mathematics
  • proof automation
  • optimization

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Georgiev, B., Gómez-Serrano, J., Tao, T., & Wagner, A. Z. (2026). Mathematical discovery and exploration can be done at scale. Proceedings of the National Academy of Sciences, 123(40), e2536158123. https://doi.org/10.1073/pnas.2536158123

How many times has this paper been cited?

161 times, according to OpenAlex on 17 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at Proceedings of the National Academy of Sciences: sign in and open the full text from this page.

Who wrote this paper?

Bogdan Georgiev, Javier Gómez-Serrano, Terence Tao, Adam Zsolt Wagner.

What is the DOI of this paper?

10.1073/pnas.2536158123, permanently at https://doi.org/10.1073/pnas.2536158123. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 17 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.