Agentic Discovery of Exchange-Correlation Density Functionals
For computational chemists and materials scientists, this work introduces an automated approach to functional design, though the need for explicit constraints reveals limitations.
The authors developed an LLM-driven agentic search system to automatically design exchange-correlation density functionals, discovering SAFS26-a which improves upon the ωB97M-V baseline by ~9% on a thermochemistry benchmark. They also highlight the risk of AI exploiting unphysical shortcuts without domain constraints.
The development of accurate exchange-correlation (XC) functionals remains a longstanding challenge in density functional theory (DFT). The vast majority of XC functionals have been hand designed by human researchers combining physical insight, exact constraints, and empirical fitting. Recent advances in large language models enable a systematic, automated alternative to this human-driven design loop. This report presents an agentic search system in which an LLM proposes structured functional-form changes guided by evolutionary history. The system attempts to improve functional performance through an iterative plan-execute-summarize loop, where improvements are measurable by optimizing functional parameters against a standard thermochemistry dataset, then evaluating performance on a held-out subset. The strongest discovered functional, SAFS26-a (Seed Agentic Functional Search 2026), improves upon the gold-standard ωB97M-V baseline by ~9%. These results also surface a cautionary lesson for AI-assisted science: models powerful enough to discover genuine improvements are equally capable of exploiting unphysical shortcuts to game the benchmark; domain expertise translated into explicitly enforced constraints remains essential to keeping results scientifically grounded.