A self-evolving agent for explainable diagnosis of DFT-experiment band-gap mismatch

TL;DR

XDFT is an autonomous agent that diagnoses and explains discrepancies in DFT predictions of material properties by iteratively testing hypotheses and updating beliefs, significantly improving diagnosis accuracy.

Contribution

The paper introduces XDFT, a self-evolving, closed-loop system that automates diagnosis of DFT mismatches using Bayesian inference and hypothesis testing, advancing explainable computational materials science.

Findings

XDFT correctly identified resolving mechanisms in 78% of mismatch cases.

XDFT outperformed random and static LLM baselines by an order of magnitude.

Resolved cases follow a simple element-class taxonomy distilled into four rules.

Abstract

Standard density functional theory (DFT) routinely misclassifies the electronic ground state of correlated and structurally complex compounds, predicting metallic behaviour for materials that experiments report as semiconductors. Each such mismatch encodes a specific non-ideality -- magnetic ordering, electron correlation, an alternative polymorph, or a defect -- that the calculation excluded, but extracting that signal at scale has remained a manual exercise. Here we introduce XDFT, a closed-loop agent that diagnoses the mismatch automatically: it draws candidate hypotheses from a curated catalogue, executes the corresponding first-principles tests, and updates a global Bayesian posterior over hypothesis usefulness from each verdict. On a verified benchmark of 124 materials, XDFT identifies a resolving mechanism for 70 of 90 mismatch cases (78\%), an order of magnitude above a uniform-random baseline (19\%) and a static LLM ordering (20\%). The internal posterior aligns with empirical performance over the benchmark timeline, and resolved cases collapse into a tri-partite element-class taxonomy that we distil into a four-line static rule. Each diagnosed material is returned with a corrected protocol and a mechanistic attribution; failed cases are flagged as evidence-backed targets for experimental re-examination.