| title | Optimizing the Optimizer: Language Models Discover Faster Molecular Relaxation |
|---|---|
| authors | Artem Tsypin, Vladimir Deshchenya, Kuzma Khrabrov, Denis Potapov, Maxim Radchenko, Artur Kadurin, Michael G. Medvedev |
| date | 2026-10-05 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.06577 |
| upvotes | 21 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Geometry optimization is a major cost in many quantum-chemical workflows: each optimization step requires one force evaluation, and at the density-functional level that evaluation dominates the wall time. Research in this area has produced a broad range of optimization methods, and we ask whether a language model can improve on the best of them through autoresearch. An agent rewrites the optimizer itself to minimize force-call counts, restrained by two admission gates that reject premature stopping and improvements that do not generalize to unseen molecules. Starting from Sella, the fastest open-source optimizer available, the search produces AutoSella, a family of two optimizers. Both of them deliver consistent force-call reductions relative to Sella across held-out molecular benchmarks and potentials not used during the search. Most notably, at the r2SCAN-3c DFT level, the best variant requires only 40.2--77.2% of Sella's force calls while achieving the same energy reduction, even though agent used no DFT gradients. |
cite
@misc{tsypin2026optimizing,
title={Optimizing the Optimizer: Language Models Discover Faster Molecular Relaxation},
author={Artem Tsypin and Vladimir Deshchenya and Kuzma Khrabrov and Denis Potapov and Maxim Radchenko and Artur Kadurin and Michael G. Medvedev},
year={2026},
eprint={2610.06577},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.06577}
}