Pushing the accuracy of on-top functionals with agent-driven supervised learning
Abstract
Multiconfiguration pair-density functional theory (MC-PDFT) combines multiconfigurational reference wave functions with on-top functionals to provide an efficient electronic-structure method for strongly correlated molecular systems. We developed a large language model-based agent for functional development and combined multiple databases into the large, chemically diverse MCDDB26 database. We then used MCDDB26 to develop two on-top functionals, MC26 and COF26. MC26 retains an existing analytical form but substantially improves performance by refitting its linear parameters with optimised weights for the training datasets. Building on this result, we developed COF26, a general hybrid on-top functional with a new analytical form. COF26 provides greater overall accuracy for multireference chemistry than existing on-top functionals. Applications across MCDDB26 show that COF26 accommodates both multiconfigurational and single-configuration densities. It therefore performs well for barrier heights, isomerisation energies, thermochemistry, non-covalent interactions, radical and non-radical chemistry, single-reference and multireference systems, and transition-metal chemistry.
Related
- DPA4: Pushing the Accuracy-Cost Frontier of Interatomic Potentials with EMFA SO(2) Convolution
- RS-CIDER: A non-local machine learning model for approximating screened hybrid functionals
- Toward Chemical Accuracy in Biomolecular Simulations through Data-Driven Many-Body Potentials: III. A Library of Amino Acid Building Blocks
- What Does a Semilocal Machine-Learning Correction Actually Learn? Size-Dependent Errors across Four Parent Functionals
- Accuracy, Reliability, and Efficiency of a MACE Machine-Learning Interatomic Potential for Aspirin: A Reproducible Benchmark for Molecular Simulation
BibTeX
@misc{chen2026pushing,
title = {{Pushing the accuracy of on-top functionals with agent-driven supervised learning}},
author = {Yuhao Chen and Dayou Zhang and Donald G. Truhlar and Xiao He},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2605.06215},
eprint = {2605.06215},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.06215},
}
RIS
TY - UNPB
TI - Pushing the accuracy of on-top functionals with agent-driven supervised learning
AU - Yuhao Chen
AU - Dayou Zhang
AU - Donald G. Truhlar
AU - Xiao He
PY - 2026
DA - 2026/09/28
PB - arXiv
DO - 10.48550/arxiv.2605.06215
UR - https://arxiv.org/abs/2605.06215
AB - Multiconfiguration pair-density functional theory (MC-PDFT) combines multiconfigurational reference wave functions with on-top functionals to provide an efficient electronic-structure method for strongly correlated molecular systems. We developed a large language model-based agent for functional development and combined multiple databases into the large, chemically diverse MCDDB26 database. We then used MCDDB26 to develop two on-top functionals, MC26 and COF26. MC26 retains an existing analytical form but substantially improves performance by refitting its linear parameters with optimised weights for the training datasets. Building on this result, we developed COF26, a general hybrid on-top functional with a new analytical form. COF26 provides greater overall accuracy for multireference chemistry than existing on-top functionals. Applications across MCDDB26 show that COF26 accommodates both multiconfigurational and single-configuration densities. It therefore performs well for barrier heights, isomerisation energies, thermochemistry, non-covalent interactions, radical and non-radical chemistry, single-reference and multireference systems, and transition-metal chemistry.
ER -