Pushing the accuracy of on-top functionals with agent-driven supervised learning

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.