This work presents a decoupled framework for multi-step computational chemistry automation built on OpenClaw. OpenClaw serves as the general-purpose agent for task coordination and supervision. Planning skills externalize task descriptions into executable task specifications, domain skills provide computational chemistry procedures, and the DPDispatcher skill grounds computation in heterogeneous HPC environments. In a methane-oxidation reactive MD case study, the framework coordinated cross-tool execution, supported bounded recovery from runtime failures, and extracted reaction networks.
Cite
@article{arxiv.2603.25522,
title = {Automating Computational Chemistry Workflows via OpenClaw and Domain-Specific Skills},
author = {Mingwei Ding and Chen Huang and Yibo Hu and Yifan Li and Zitian Lu and Xingtai Yu and Duo Zhang and Wenxi Zhai and Tong Zhu and Qiangqiang Gu and Jinzhe Zeng},
journal= {arXiv preprint arXiv:2603.25522},
year = {2026}
}