FunctionalAgent: Towards end-to-end on-top functional design

TL;DR

FunctionalAgent automates the development of on-top functionals for multiconfiguration pair-density functional theory, leading to new functionals with improved accuracy through an end-to-end workflow.

Contribution

We introduce FunctionalAgent, an automated system that streamlines the creation of on-top functionals, resulting in the development of MC26 and COF26 with enhanced predictive performance.

Findings

MC26 outperforms existing methods on the benchmark dataset.

COF26 achieves the best results on both training and test sets.

Automated workflow improves functional development efficiency.

Abstract

Multiconfiguration pair-density functional theory (MC-PDFT) offers an efficient and accurate framework for computing electronic energies in strongly correlated molecular systems, with the quality of the on-top functional being a key determinant of its predictive accuracy. Here we introduce FunctionalAgent, an agentic system for fully automated functional development. FunctionalAgent orchestrates a team of specialized sub-agents to decompose the development process into dataset construction, active-space generation, MCSCF calculation and descriptor generation, loss-function construction, and functional fitting, optimization, and evaluation, thereby linking all stages into a closed-loop automated workflow. Using FunctionalAgent, we developed MC26, a hybrid meta-GGA on-top functional that achieves improved overall accuracy on the training set compared with other methods evaluated on the same benchmark dataset. We further introduce COF26, a new functional form that, owing to the optimized training process, achieves the best performance on both the training and test sets.