DefectSkills: Guiding AI agents through first-principles calculations for point defects in semiconductors and insulators
Abstract
First-principles defect calculations can now be performed autonomously by AI agents, enabled by established computational methods and open-source Python toolkits. However, reliable and repeatable defect calculations require clear scientific and technical guidance that helps agents resolve ambiguities and avoid errors in calculation setup, execution, postprocessing, and analysis. Here, we present DefectSkills, a set of structured prompts that provides human-in-the-loop guidance to AI agents performing first-principles calculations of point defects in semiconductors and insulators using the Vienna Ab initio Simulation Package (VASP). The prompts encode human expertise and guide agents through unit-cell relaxation, electronic-structure and dielectric calculations, phase-stability and chemical-potential analysis, charged-defect supercell generation and calculations, finite-size corrections, formation-energy calculations and thermodynamic analysis, and data backup. By packaging this expertise as reusable agent skills, DefectSkills supports consistent workflow execution across agentic AI systems and reproducible defect calculations.
Related
- First-Principles Calculations of the Electron-Hole-Pair Creation Energy in Semiconductors and Dielectrics
- Coherent phonons in photoexcited semiconductors from first principles
- Y2CdX4 (X = S, Se, Te) Semiconductors: A First-Principles Study of Structural, Electronic, Optical, and Energy-Related Properties
- First-principles calculations of electronic structure
- Structural and Electronic Properties of Bulk β(2H)-GaSe from First-Principles DFT Calculations with van der Waals Corrections
BibTeX
@misc{yuan2026defectskills,
title = {{DefectSkills: Guiding AI agents through first-principles calculations for point defects in semiconductors and insulators}},
author = {Zhenkun Yuan and Yizhi Zhu and Geoffroy Hautier},
howpublished = {arXiv},
year = {2026},
month = nov,
doi = {10.48550/arxiv.2611.05654},
eprint = {2611.05654},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2611.05654},
}
RIS
TY - UNPB
TI - DefectSkills: Guiding AI agents through first-principles calculations for point defects in semiconductors and insulators
AU - Zhenkun Yuan
AU - Yizhi Zhu
AU - Geoffroy Hautier
PY - 2026
DA - 2026/11/03
PB - arXiv
DO - 10.48550/arxiv.2611.05654
UR - https://arxiv.org/abs/2611.05654
AB - First-principles defect calculations can now be performed autonomously by AI agents, enabled by established computational methods and open-source Python toolkits. However, reliable and repeatable defect calculations require clear scientific and technical guidance that helps agents resolve ambiguities and avoid errors in calculation setup, execution, postprocessing, and analysis. Here, we present DefectSkills, a set of structured prompts that provides human-in-the-loop guidance to AI agents performing first-principles calculations of point defects in semiconductors and insulators using the Vienna Ab initio Simulation Package (VASP). The prompts encode human expertise and guide agents through unit-cell relaxation, electronic-structure and dielectric calculations, phase-stability and chemical-potential analysis, charged-defect supercell generation and calculations, finite-size corrections, formation-energy calculations and thermodynamic analysis, and data backup. By packaging this expertise as reusable agent skills, DefectSkills supports consistent workflow execution across agentic AI systems and reproducible defect calculations.
ER -