Preprint · 2025 · Open access

AlphaEvolve: A coding agent for scientific and algorithmic discovery

Novikov, Alexander, Vũ, Ngân, Eisenberger, Marvin, Emilien Dupont, Po-Sen Huang, Adam Zsolt Wagner, S. Shirobokov, Borislav M. Kozlovskii, Francisco J. R. Ruiz, Abbas Mehrabian, Manish Kumar, Abigail See and 6 more

arXiv (Cornell University) · Published 16 June 2025 · DOI 10.48550/arxiv.2506.13131

Open PDFView at the publisherCite this paper

In brief

“AlphaEvolve: A coding agent for scientific and algorithmic discovery” is a 2025 preprint by Novikov, Alexander and 17 co-authors, published in arXiv (Cornell University). OpenAlex counts 1,656 citations as of 18 November 2026. It is open access: the full text is free to read at arXiv (Cornell University).

Citations
1,656
Most cited in
2026 (1,423)
References
95
Authors
18

Abstract

In this white paper, we present AlphaEvolve, an evolutionary coding agent that substantially enhances capabilities of state-of-the-art LLMs on highly challenging tasks such as tackling open scientific problems or optimizing critical pieces of computational infrastructure. AlphaEvolve orchestrates an autonomous pipeline of LLMs, whose task is to improve an algorithm by making direct changes to the code. Using an evolutionary approach, continuously receiving feedback from one or more evaluators, AlphaEvolve iteratively improves the algorithm, potentially leading to new scientific and practical discoveries. We demonstrate the broad applicability of this approach by applying it to a number of important computational problems. When applied to optimizing critical components of large-scale computational stacks at Google, AlphaEvolve developed a more efficient scheduling algorithm for data centers, found a functionally equivalent simplification in the circuit design of hardware accelerators, and accelerated the training of the LLM underpinning AlphaEvolve itself. Furthermore, AlphaEvolve discovered novel, provably correct algorithms that surpass state-of-the-art solutions on a spectrum of problems in mathematics and computer science, significantly expanding the scope of prior automated discovery methods (Romera-Paredes et al., 2023). Notably, AlphaEvolve developed a search algorithm that found a procedure to multiply two $4 \times 4$ complex-valued matrices using $48$ scalar multiplications; offering the first improvement, after 56 years, over Strassen's algorithm in this setting. We believe AlphaEvolve and coding agents like it can have a significant impact in improving solutions of problems across many areas of science and computation.

Cite this paper

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

APA 7

Alexander, N., Ngân, V., Marvin, E., Dupont, E., Huang, P.-S., Wagner, A. Z., Shirobokov, S., Kozlovskii, B. M., Ruiz, F. J. R., Mehrabian, A., Kumar, M., See, A., Chaudhuri, S., George, H., Davies, A., Nowozin, S., Kohli, P., & Balog, M. (2025). AlphaEvolve: A coding agent for scientific and algorithmic discovery. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2506.13131

MLA 9

Alexander, Novikov,, et al. “AlphaEvolve: A coding agent for scientific and algorithmic discovery.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2506.13131.

Chicago

Alexander, Novikov,, Vũ, Ngân, Eisenberger, Marvin, Emilien Dupont, Po-Sen Huang, Adam Zsolt Wagner, S. Shirobokov, et al. 2025. “AlphaEvolve: A coding agent for scientific and algorithmic discovery.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2506.13131.

Harvard

Alexander, N. et al. (2025) ‘AlphaEvolve: A coding agent for scientific and algorithmic discovery’, arXiv (Cornell University). doi:10.48550/arxiv.2506.13131.

IEEE

N. Alexander et al., “AlphaEvolve: A coding agent for scientific and algorithmic discovery,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2506.13131.

BibTeX

@misc{alexander2025alphaevolve,
  title     = {{AlphaEvolve: A coding agent for scientific and algorithmic discovery}},
  author    = {Alexander, Novikov, and Ngân, Vũ, and Marvin, Eisenberger, and Dupont, Emilien and Huang, Po-Sen and Wagner, Adam Zsolt and Shirobokov, S. and Kozlovskii, Borislav M. and Ruiz, Francisco J. R. and Mehrabian, Abbas and Kumar, Manish and See, Abigail and Chaudhuri, Swarat and George, Holland, and Davies, Alex and Nowozin, Sebastian and Kohli, Pushmeet and Balog, Matej},
  howpublished = {arXiv (Cornell University)},
  year      = {2025},
  doi       = {10.48550/arxiv.2506.13131},
  url       = {https://doi.org/10.48550/arxiv.2506.13131}
}

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

  • coding agents
  • evolutionary algorithms
  • large language models
  • data center scheduling
  • Strassen's algorithm
  • matrix multiplication
  • scientific discovery

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?

Alexander, N., Ngân, V., Marvin, E., Dupont, E., Huang, P.-S., Wagner, A. Z., Shirobokov, S., Kozlovskii, B. M., Ruiz, F. J. R., Mehrabian, A., Kumar, M., See, A., Chaudhuri, S., George, H., Davies, A., Nowozin, S., Kohli, P., & Balog, M. (2025). AlphaEvolve: A coding agent for scientific and algorithmic discovery. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2506.13131

How many times has this paper been cited?

1,656 times, according to OpenAlex on 18 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 arXiv (Cornell University): sign in and open the PDF from this page.

Who wrote this paper?

Novikov, Alexander, Vũ, Ngân, Eisenberger, Marvin, Emilien Dupont, Po-Sen Huang, Adam Zsolt Wagner, S. Shirobokov, Borislav M. Kozlovskii, Francisco J. R. Ruiz, Abbas Mehrabian, Manish Kumar, Abigail See and 6 more.

What is the DOI of this paper?

10.48550/arxiv.2506.13131, permanently at https://doi.org/10.48550/arxiv.2506.13131. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 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.