Science Done on a Machine by a Machine: AI Agents in Computational Chemistry
Abstract
We are witnessing an explosion of agentic systems for computational chemistry: from four in 2024 to seventeen in 2025 and over sixty now, surveyed here. What is delegated to these systems is shifting from single calculations to whole in silico experiments and even manuscript writing. The ultimate destination is a fully autonomous AI scientist, where the entirety of computational chemistry is performed on a machine by a machine, without human supervision. Our survey shows that these systems are turning into vetted chemistry skills on general-purpose coding agents, and that they must be evaluated not only on their final answers but also on whether their calculations actually support these answers. The role of the human computational chemist is shifting from performing calculations to directing and supervising them, and the field should invest in the judgement that makes the supervision reliable: we propose a reporting standard, an evaluation reproducing published studies, a controlled comparison with general-purpose coding agents, and how to teach.
Related
- Natural Product Chemistry in Sickle Cell Disease Therapeutics: Phytochemical Mechanisms, Pharmacokinetics, and Computational Docking Insights for Next-Generation Anti-Sickling Agents: A Comprehensive Review
- Integrating Generative AI and Data Science into General Chemistry Laboratories
- From Execution to Discovery : Physical Verification as the Key Gap in AI Agents for Science
- vibyverse: an integrated computational chemistry ecosystem developed through agentic engineering
- Making Complete-Basis-Set Extrapolation Visible: A Spreadsheet-Based Activity for Upper-Division Computational Chemistry
BibTeX
@misc{dral2026science,
title = {{Science Done on a Machine by a Machine: AI Agents in Computational Chemistry}},
author = {Pavlo O. Dral and Hassan Nawaz and Arif Ullah},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2608.18508},
eprint = {2608.18508},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.18508},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Science Done on a Machine by a Machine: AI Agents in Computational Chemistry
AU - Pavlo O. Dral
AU - Hassan Nawaz
AU - Arif Ullah
PY - 2026
DA - 2026/10/05
PB - arXiv
DO - 10.48550/arxiv.2608.18508
UR - https://arxiv.org/abs/2608.18508
AB - We are witnessing an explosion of agentic systems for computational chemistry: from four in 2024 to seventeen in 2025 and over sixty now, surveyed here. What is delegated to these systems is shifting from single calculations to whole in silico experiments and even manuscript writing. The ultimate destination is a fully autonomous AI scientist, where the entirety of computational chemistry is performed on a machine by a machine, without human supervision. Our survey shows that these systems are turning into vetted chemistry skills on general-purpose coding agents, and that they must be evaluated not only on their final answers but also on whether their calculations actually support these answers. The role of the human computational chemist is shifting from performing calculations to directing and supervising them, and the field should invest in the judgement that makes the supervision reliable: we propose a reporting standard, an evaluation reproducing published studies, a controlled comparison with general-purpose coding agents, and how to teach.
ER -