Preprint · 2025 · Open access
Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learning
arXiv (Cornell University) · Published 7 April 2025 · DOI 10.48550/arxiv.2504.05108
In brief
“Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learning” is a 2025 preprint by Anja Surina and 6 co-authors, published in arXiv (Cornell University). OpenAlex counts 61 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).
- Citations
- 61
- Most cited in
- 2026 (41)
- References
- 61
- Authors
- 7
Abstract
Discovering efficient algorithms for solving complex problems has been an outstanding challenge in mathematics and computer science, requiring substantial human expertise over the years. Recent advancements in evolutionary search with large language models (LLMs) have shown promise in accelerating the discovery of algorithms across various domains, particularly in mathematics and optimization. However, existing approaches treat the LLM as a static generator, missing the opportunity to update the model with the signal obtained from evolutionary exploration. In this work, we propose to augment LLM-based evolutionary search by continuously refining the search operator - the LLM - through reinforcement learning (RL) fine-tuning. Our method leverages evolutionary search as an exploration strategy to discover improved algorithms, while RL optimizes the LLM policy based on these discoveries. Our experiments on combinatorial optimization tasks demonstrate that integrating RL with evolutionary search accelerates the discovery of superior algorithms, showcasing the potential of RL-enhanced evolutionary strategies for algorithm design.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Surina, A., Mansouri, A., Quaedvlieg, L. C. P. M., Seddas, A., Viazovska, M., Abbe, E. A., & Gülçehre, Ç. (2025). Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learning. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2504.05108
MLA 9
Surina, Anja, et al. “Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learning.” arXiv (Cornell University), 2025. https://doi.org/10.48550/arxiv.2504.05108.
Chicago
Surina, Anja, Amin Mansouri, Lars C. P. M. Quaedvlieg, Amal Seddas, Maryna Viazovska, Emmanuel A. Abbe, and Çağlar Gülçehre. 2025. “Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learning.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2504.05108.
Harvard
Surina, A. et al. (2025) ‘Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learning’, arXiv (Cornell University). doi:10.48550/arxiv.2504.05108.
IEEE
A. Surina et al., “Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learning,” arXiv (Cornell University), 2025, doi: 10.48550/arxiv.2504.05108.
BibTeX
@misc{surina2025algorithm,
title = {{Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learning}},
author = {Surina, Anja and Mansouri, Amin and Quaedvlieg, Lars C. P. M. and Seddas, Amal and Viazovska, Maryna and Abbe, Emmanuel A. and Gülçehre, Çağlar},
howpublished = {arXiv (Cornell University)},
year = {2025},
doi = {10.48550/arxiv.2504.05108},
url = {https://doi.org/10.48550/arxiv.2504.05108}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Citations by year
| Year | Citations | Share of the best year |
|---|---|---|
| 2024 | 1 | |
| 2025 | 19 | |
| 2026 | 41 |
Topic and keywords
Physical Sciences › Computer Science › Artificial Intelligence › Evolutionary Algorithms and Applications
- algorithm discovery
- large language models
- evolutionary search
- reinforcement learning fine-tuning
- combinatorial optimization
- algorithm design
Work with this paper
Most-cited papers in Computer Science
- ImageNet classification with deep convolutional neural networksAlex Krizhevsky, Ilya Sutskever, Geoffrey E. Hinton · Communications of the ACM · 2017 · 114,726 citations
- Long Short-Term MemorySepp Hochreiter, Jürgen Schmidhuber · Neural Computation · 1997 · 109,097 citations
- A Mathematical Theory of CommunicationClaude E. Shannon · Bell System Technical Journal · 1948 · 91,736 citations
- Deep learningYann LeCun, Yoshua Bengio, Geoffrey E. Hinton · Nature · 2015 · 90,226 citations
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal NetworksShaoqing Ren, Kaiming He, Ross Girshick and 1 more · IEEE Transactions on Pattern Analysis and Machine Intelligence · 2016 · 74,143 citations
Questions about this paper
How do I cite this paper in APA style?
Surina, A., Mansouri, A., Quaedvlieg, L. C. P. M., Seddas, A., Viazovska, M., Abbe, E. A., & Gülçehre, Ç. (2025). Algorithm Discovery With LLMs: Evolutionary Search Meets Reinforcement Learning. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2504.05108
How many times has this paper been cited?
61 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?
Anja Surina, Amin Mansouri, Lars C. P. M. Quaedvlieg, Amal Seddas, Maryna Viazovska, Emmanuel A. Abbe, Çağlar Gülçehre.
What is the DOI of this paper?
10.48550/arxiv.2504.05108, permanently at https://doi.org/10.48550/arxiv.2504.05108. 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.