Paper · 2025 · Open access
Cross-Domain Mathematical Problem Solving with a Human-AI Hybrid Recursive System: Benchmarking Against AlphaEvolve and Google Systems
Zenodo (CERN European Organization for Nuclear Research) · Published 18 November 2025 · DOI 10.5281/zenodo.17635862
In brief
“Cross-Domain Mathematical Problem Solving with a Human-AI Hybrid Recursive System: Benchmarking Against AlphaEvolve and Google Systems” is a 2025 paper by Stieve, Jonathan, published in Zenodo (CERN European Organization for Nuclear Research). OpenAlex counts 0 citations as of 18 November 2026. It is open access under a CC BY licence: the full text is free to read at Zenodo (CERN European Organization for Nuclear Research).
- Citations
- 0
- Authors
- 1
Abstract
The results of our human-AI hybrid recursive system demonstrate a clear performance advantage over existing automated solvers. Compared to AlphaEvolve and Google’s state-of-the-art mathematical reasoning systems, our system not only rediscovered all known optimal constructions but also generated novel solutions for previously unsolved instances, such as n = 21, 26, and 32 in the Circle Packing problem. Notably, it improved the previously established upper bound for n = 11 from 3.89453 to 2.89453, representing a significant enhancement in solution quality. These results were achieved on consumer-grade laptop hardware, leveraging real-world data integration and co-evolutionary human-AI loops, illustrating that high-impact mathematical discovery can be performed efficiently outside traditional high-performance computing environments.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Jonathan, S. (2025). Cross-Domain Mathematical Problem Solving with a Human-AI Hybrid Recursive System: Benchmarking Against AlphaEvolve and Google Systems. Zenodo (CERN European Organization for Nuclear Research). https://doi.org/10.5281/zenodo.17635862
MLA 9
Jonathan, Stieve,. “Cross-Domain Mathematical Problem Solving with a Human-AI Hybrid Recursive System: Benchmarking Against AlphaEvolve and Google Systems.” Zenodo (CERN European Organization for Nuclear Research), 2025. https://doi.org/10.5281/zenodo.17635862.
Chicago
Jonathan, Stieve,. 2025. “Cross-Domain Mathematical Problem Solving with a Human-AI Hybrid Recursive System: Benchmarking Against AlphaEvolve and Google Systems.” Zenodo (CERN European Organization for Nuclear Research). https://doi.org/10.5281/zenodo.17635862.
Harvard
Jonathan, S. (2025) ‘Cross-Domain Mathematical Problem Solving with a Human-AI Hybrid Recursive System: Benchmarking Against AlphaEvolve and Google Systems’, Zenodo (CERN European Organization for Nuclear Research). doi:10.5281/zenodo.17635862.
IEEE
S. Jonathan, “Cross-Domain Mathematical Problem Solving with a Human-AI Hybrid Recursive System: Benchmarking Against AlphaEvolve and Google Systems,” Zenodo (CERN European Organization for Nuclear Research), 2025, doi: 10.5281/zenodo.17635862.
BibTeX
@article{jonathan2025cross,
title = {{Cross-Domain Mathematical Problem Solving with a Human-AI Hybrid Recursive System: Benchmarking Against AlphaEvolve and Google Systems}},
author = {Jonathan, Stieve,},
journal = {Zenodo (CERN European Organization for Nuclear Research)},
year = {2025},
doi = {10.5281/zenodo.17635862},
url = {https://doi.org/10.5281/zenodo.17635862}
}
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
- hybrid human-AI systems
- mathematical problem solving
- circle packing
- upper bounds
- benchmarking
- low-cost hardware
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?
Jonathan, S. (2025). Cross-Domain Mathematical Problem Solving with a Human-AI Hybrid Recursive System: Benchmarking Against AlphaEvolve and Google Systems. Zenodo (CERN European Organization for Nuclear Research). https://doi.org/10.5281/zenodo.17635862
How many times has this paper been cited?
0 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 Zenodo (CERN European Organization for Nuclear Research): sign in and open the full text from this page.
Who wrote this paper?
Stieve, Jonathan.
What is the DOI of this paper?
10.5281/zenodo.17635862, permanently at https://doi.org/10.5281/zenodo.17635862. 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.