cs.AINov 9, 2026

Agent-Guided Discovery of Exchange-Correlation Functionals with Physics-based Validation

Authors: Achuth Chandrasekhar, Amir Barati Farimani

Organizations: Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA · Biomedical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA · Chemical Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA · Materials Science and Engineering, Carnegie Mellon University, Pittsburgh, PA 15213, USA · 

Abstract

Accurate, compact exchange--correlation functionals are central to predictive density functional theory. Symbolic search and language-model agents can propose new functional forms, but it remains unclear whether their gains survive self-consistency and external evaluation, whether the new terms carry physical content, whether agents outperform evolutionary search, and how language-model backbones compare. We connect frontier LLM agents to a GPU evaluator through the Model Context Protocol, with training-only fitting, persistent memory, and self-consistent and external evaluation. Opus-5.5 agents passed the screening gate with about 40-fold fewer tokens than Codex (GPT-6-Astra) agents and found a candidate with lower validation and held-out errors; only this candidate advanced to self-consistent evaluation. The resulting 13-parameter functional, O159, multiplies same-spin correlation by a smooth density window. Refitted controls favor a window that scales the entire same-spin factor, reducing it by 15--30% at its peak, and that acts on reaction energies mainly in near-iso-orbital regions; against a refitted no-window control, it lowers heavy-atom total-energy errors on GSCDB137 by 29%. With about 400 fits each, SyFES evolution did not improve on its GAS22 seed, whereas the agents found forms 0.10--0.13 \kcal\ lower in validation error by adding an explicit density scale. Self-consistent O159 lowers the held-out MGCDB84 test error of ωωB97M-V by 11.7%, and its mean normalized error ratio on 36 GSCDB137 datasets (1.139) is comparable to ωωB97M-V (1.144) and below GAS22 (1.190). Frontier-LLM agents thus produced O159, a compact functional whose improvement over ωωB97M-V survives self-consistent, physics-based validation.

Figures & tables

Explore similar work

CardsList
  1. Agentic Discovery of Exchange-Correlation Density Functionals

    May 6, 2026Titouan Duston, Jiashu Liang, Yuanheng Wang +6Quantum ChemistryDensity Functional Theory

  2. Density Constraints Overcome the Energy-Density Trade-Off in Exchange-Correlation Functionals

    Oct 21, 2026Yuhao Chen, Donald G. Truhlar, Xiao HeDensity Functional TheoryComputational Quantum Chemistry

  3. Derivative Informed Learning of Exchange-Correlation Functionals

    Jun 2, 2026Eike S. Eberhard, Luca A. Thiede, Abdul Aldossary +5Quantum ChemistryDensity Functional Theory