Preprint · 2026 · Open access
ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search
arXiv (Cornell University) · Published 10 February 2026 · DOI 10.48550/arxiv.2602.10233
In brief
“ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search” is a 2026 preprint by Alexey Kravatskiy and 2 co-authors, published in arXiv (Cornell University). OpenAlex counts 5 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
- 5
- Most cited in
- 2026 (5)
- References
- 13
- Authors
- 3
Abstract
LLM-guided evolutionary computation, most notably AlphaEvolve, has been remarkably successful in discovering novel mathematical constructions by solving challenging optimization problems. The standard approach is to evolve a monolithic program that directly outputs a candidate solution. We present ImprovEvolve, an algorithmic alternative that drastically reduces cognitive load on the LLM. Instead of prompting the model for an end-to-end optimizer, we evolve a program with three specialized operators of initialization, local improvement, and perturbation. We then approach the optimum by iteratively applying local improvements and intensity-scheduled perturbations, effectively driving a basin-hopping search with LLM-evolved subroutines. For hexagon in hexagon packing, ImprovEvolve discovers new state-of-the-art packings of 11, 12, 15, and 16 hexagons, and additionally for 14, 17, and 23 hexagons after minimal expert tuning of the generated code. For the second autocorrelation inequality, the evolved and human-scaled program pushes the lower bound from 0.96102 to 0.96258. For spherical codes, the ImprovEvolve program lowers the best-known maximum cosine for the majority of 90 randomly chosen diverse state-of-the-art spherical codes, achieving relative improvements of up to 2.4%.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Kravatskiy, A., Khrulkov, V., & Oseledets, I. (2026). ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.10233
MLA 9
Kravatskiy, Alexey, et al. “ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2602.10233.
Chicago
Kravatskiy, Alexey, Valentin Khrulkov, and Ivan Oseledets. 2026. “ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.10233.
Harvard
Kravatskiy, A., Khrulkov, V. and Oseledets, I. (2026) ‘ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search’, arXiv (Cornell University). doi:10.48550/arxiv.2602.10233.
IEEE
A. Kravatskiy, V. Khrulkov, and I. Oseledets, “ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2602.10233.
BibTeX
@misc{kravatskiy2026improvevolve,
title = {{ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search}},
author = {Kravatskiy, Alexey and Khrulkov, Valentin and Oseledets, Ivan},
howpublished = {arXiv (Cornell University)},
year = {2026},
doi = {10.48550/arxiv.2602.10233},
url = {https://doi.org/10.48550/arxiv.2602.10233}
}
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
- basin hopping
- spherical codes
- software evolution
- optimization
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?
Kravatskiy, A., Khrulkov, V., & Oseledets, I. (2026). ImprovEvolve: Basin-Hopping Meets LLM-Guided Evolutionary Search. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2602.10233
How many times has this paper been cited?
5 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?
Alexey Kravatskiy, Valentin Khrulkov, Ivan Oseledets.
What is the DOI of this paper?
10.48550/arxiv.2602.10233, permanently at https://doi.org/10.48550/arxiv.2602.10233. 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.