# Agentic Discovery of Exchange-Correlation Density Functionals

arXiv: https://arxiv.org/abs/2605.05460 · HTML: https://mlsanity.com/paper/2605.05460/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 21 references that are in the map.
- First posted on arXiv 6 May 2026.

## Builds on (most cited first, 5 of 5)

- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution](https://mlsanity.com/paper/2502.18449/) (2025)
- [Accelerating Scientific Research with Gemini: Case Studies and Common Techniques](https://mlsanity.com/paper/2602.03837/) (2026)
- [LoongFlow: Directed Evolutionary Search via a Cognitive Plan-Execute-Summarize Paradigm](https://mlsanity.com/paper/2512.24077/) (2025)
- [Evolving symbolic density functionals](https://mlsanity.com/paper/2203.02540/) (2022)

## Abstract (arXiv)

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.