Preprint · 2026 · Open access

Learning consistent molecular mechanics force fields from first principles

Berkay Günes, Leif Seute, Jigyasa Nigam, Frauke Gräter

arXiv (Cornell University) · Published 6 October 2026 · DOI 10.48550/arxiv.2610.08020

Free PDFView at the publisherCite this paper

In brief

“Learning consistent molecular mechanics force fields from first principles” is a 2026 preprint by Berkay Günes and 3 co-authors, published in arXiv (Cornell University). OpenAlex counts 0 citations as of 16 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
0
References
30
Authors
4

Abstract

Classical force fields (FFs) remain the workhorse for large-scale simulations even as machine-learned interatomic potentials (MLIPs) approach ab initio accuracy. They decompose total configuration energies into simple effective interactions whose parameters are traditionally assigned based on atom or bond types, enabling efficient simulations but also limiting their ability to adapt across configurations. Recent machine learning approaches have improved the accuracy and transferability of bonded parameters in these FFs by inferring them as functions of local atomic environments, but still rely on empirical nonbonded parameters for practical simulations. In this work, we introduce a unified approach, \texttt{grappa-fullFF}, which learns both bonded and nonbonded parameters \emph{consistently} and simultaneously from ab initio reference data. By incorporating physically inspired regularization via supervision of the electrostatic potential and an architecture that facilitates charge equilibration, our model recovers accurate electric response properties, achieves state-of-the-art accuracy on geometry optimization benchmarks, and reproduces the conformational sampling of both classical and existing machine-learned FFs, without relying on externally assigned nonbonded parameters.

Cite this paper

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

APA 7

Günes, B., Seute, L., Nigam, J., & Gräter, F. (2026). Learning consistent molecular mechanics force fields from first principles. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.08020

MLA 9

Günes, Berkay, et al. “Learning consistent molecular mechanics force fields from first principles.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2610.08020.

Chicago

Günes, Berkay, Leif Seute, Jigyasa Nigam, and Frauke Gräter. 2026. “Learning consistent molecular mechanics force fields from first principles.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.08020.

Harvard

Günes, B. et al. (2026) ‘Learning consistent molecular mechanics force fields from first principles’, arXiv (Cornell University). doi:10.48550/arxiv.2610.08020.

IEEE

B. Günes, L. Seute, J. Nigam, and F. Gräter, “Learning consistent molecular mechanics force fields from first principles,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2610.08020.

BibTeX

@misc{gunes2026learning,
  title     = {{Learning consistent molecular mechanics force fields from first principles}},
  author    = {Günes, Berkay and Seute, Leif and Nigam, Jigyasa and Gräter, Frauke},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2610.08020},
  url       = {https://doi.org/10.48550/arxiv.2610.08020}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science

  • molecular mechanics force field
  • machine learning interatomic potentials
  • charge equilibration
  • geometry optimization
  • conformational sampling
  • transferability

Work with this paper

Most-cited papers in Materials Science

All highly cited Materials Science papers

Questions about this paper

How do I cite this paper in APA style?

Günes, B., Seute, L., Nigam, J., & Gräter, F. (2026). Learning consistent molecular mechanics force fields from first principles. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2610.08020

How many times has this paper been cited?

0 times, according to OpenAlex on 16 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: read the free full text at arXiv (Cornell University).

Who wrote this paper?

Berkay Günes, Leif Seute, Jigyasa Nigam, Frauke Gräter.

What is the DOI of this paper?

10.48550/arxiv.2610.08020. The permanent link is https://doi.org/10.48550/arxiv.2610.08020.

Bibliographic data from OpenAlex (CC0), last checked 16 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.