AI RESEARCH
Agentic Discovery of Exchange-Correlation Density Functionals
arXiv CS.AI
•
ArXi:2605.05460v1 Announce Type: new 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.