An Extensible Agentic Framework for Expert-Level Automation of Atomistic Simulations
Abstract
Traditionally, atomistic simulation has been constrained by the computational scaling limits of ab initio methods and the parameterization overhead of empirical force fields. The recent emergence of universal machine learning interatomic potentials has significantly mitigated these bottlenecks, offering near-quantum accuracy and generalizability across diverse chemical spaces at a fraction of the computational cost. However, this shift has relocated the bottleneck to the human dimension: time-consuming mechanical processes, such as input preparation and data analysis, now dominate the research lifecycle. We introduce Paimon, a Platform for Agentic Integration in Materials Optimization and Nanoscale-simulations. Through hundreds of trials on an expert-level liquid electrolyte simulation, we show that Paimon substantially improves the reliability of agentic workflows by suppressing silent errors: plausible yet physically incorrect results. Paimon accommodates a new capability without modifying the agents already present, which we demonstrate by integrating an externally developed scientific agent. As an agent harness for atomistic simulations, Paimon affords researchers a continuous, science-centric workflow throughout the entire simulation lifecycle.
Related
- Aitomia: An Agentic Framework for AI-Driven Atomistic and Quantum Chemical Simulations
- KEMPIC-3D: A transparent and extensible electromagnetic Particle-in-Cell framework for kinetic plasma simulations
- Automated Many-Body Simulations of Strongly Correlated Systems Using a Correlation-Aware Agentic Framework
- Hierarchical automation of scanning probe microscopy through agentic orchestration and algorithmic control
- VoroTypes: automated enumeration of Voronoi cell topologies for structural identification of complex crystals in atomistic simulations
BibTeX
@misc{park2026extensible,
title = {{An Extensible Agentic Framework for Expert-Level Automation of Atomistic Simulations}},
author = {Yutack Park and Yeonwoo Chung and Jinmu You and Jisu Kim and Suyeon Ju and Seungwu Han},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2606.09422},
eprint = {2606.09422},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2606.09422},
}
RIS
TY - UNPB
TI - An Extensible Agentic Framework for Expert-Level Automation of Atomistic Simulations
AU - Yutack Park
AU - Yeonwoo Chung
AU - Jinmu You
AU - Jisu Kim
AU - Suyeon Ju
AU - Seungwu Han
PY - 2026
DA - 2026/10/06
PB - arXiv
DO - 10.48550/arxiv.2606.09422
UR - https://arxiv.org/abs/2606.09422
AB - Traditionally, atomistic simulation has been constrained by the computational scaling limits of ab initio methods and the parameterization overhead of empirical force fields. The recent emergence of universal machine learning interatomic potentials has significantly mitigated these bottlenecks, offering near-quantum accuracy and generalizability across diverse chemical spaces at a fraction of the computational cost. However, this shift has relocated the bottleneck to the human dimension: time-consuming mechanical processes, such as input preparation and data analysis, now dominate the research lifecycle. We introduce Paimon, a Platform for Agentic Integration in Materials Optimization and Nanoscale-simulations. Through hundreds of trials on an expert-level liquid electrolyte simulation, we show that Paimon substantially improves the reliability of agentic workflows by suppressing silent errors: plausible yet physically incorrect results. Paimon accommodates a new capability without modifying the agents already present, which we demonstrate by integrating an externally developed scientific agent. As an agent harness for atomistic simulations, Paimon affords researchers a continuous, science-centric workflow throughout the entire simulation lifecycle.
ER -