ElectrolyteMD-Bench: How Well Do AI Agents Conduct Molecular Dynamics Studies across Electrolyte Solvation Regimes?
Abstract
AI agents are advancing the automation of molecular dynamics (MD) research, with the potential to accelerate discovery and design of lithium-battery electrolytes. However, whether they can autonomously complete scientifically reliable electrolyte MD studies remains insufficiently evaluated. We introduce ElectrolyteMD-Bench, which unifies dilute, high-concentration, and localized high-concentration electrolytes in a comparative study across distinct solvation regimes. The benchmark connects local coordination, ionic association, single-particle dynamics, and collective transport within one continuous research process. Agents autonomously perform system construction, equilibration, production sampling, property analysis, and interpretation under a frozen scientific model, while deciding whether to correct errors, continue sampling, or stop. We audit each study along four dimensions: simulation validity, analysis validity, evidence integrity, and outcome calibration. Across eight model--harness configurations, all 24 system runs produced valid production trajectories, yet none of the eight studies satisfied all scientific requirements. Failures included missing analyses, incorrect physical definitions or numerical implementations, insufficient statistical support, and completion claims inconsistent with retained evidence. These results expose a gap between successful MD workflow execution and reliable scientific study completion. ElectrolyteMD-Bench therefore provides a foundational test and defines a key capability threshold that autonomous electrolyte simulation must cross to advance toward computation-first materials exploration.
Related
- Ab Initio Molecular Dynamics with Explicit Solvation Reveals the Volmer–Heyrovsky Mechanism for Chlorine Evolution on Dimensionally Stable Anodes
- Vicem: Automating Molecular Mechanics Modeling of Solvation Dynamics with Applications to Time-Resolved X-ray Scattering
- Stable lithium/electrolyte interphase enabled by tailoring Li+ solvation structure and FEC additive in LiOTf/LiNO3 dual-salt sulfolane-based nonflammable electrolyte for lithium metal batteries
- Differentiable Solvation Shell Model for Rational Electrolyte Design
- EXAFS probing of nonequilibrium solvation dynamics of nascent halogen radicals
BibTeX
@misc{wu2026electrolytemdbench,
title = {{ElectrolyteMD-Bench: How Well Do AI Agents Conduct Molecular Dynamics Studies across Electrolyte Solvation Regimes?}},
author = {Shukai Wu and Shuo Niu and Zhaoming Xu and Yan Luo and Wentao Lin},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.31743},
eprint = {2609.31743},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.31743},
}
RIS
TY - UNPB
TI - ElectrolyteMD-Bench: How Well Do AI Agents Conduct Molecular Dynamics Studies across Electrolyte Solvation Regimes?
AU - Shukai Wu
AU - Shuo Niu
AU - Zhaoming Xu
AU - Yan Luo
AU - Wentao Lin
PY - 2026
DA - 2026/09/23
PB - arXiv
DO - 10.48550/arxiv.2609.31743
UR - https://arxiv.org/abs/2609.31743
AB - AI agents are advancing the automation of molecular dynamics (MD) research, with the potential to accelerate discovery and design of lithium-battery electrolytes. However, whether they can autonomously complete scientifically reliable electrolyte MD studies remains insufficiently evaluated. We introduce ElectrolyteMD-Bench, which unifies dilute, high-concentration, and localized high-concentration electrolytes in a comparative study across distinct solvation regimes. The benchmark connects local coordination, ionic association, single-particle dynamics, and collective transport within one continuous research process. Agents autonomously perform system construction, equilibration, production sampling, property analysis, and interpretation under a frozen scientific model, while deciding whether to correct errors, continue sampling, or stop. We audit each study along four dimensions: simulation validity, analysis validity, evidence integrity, and outcome calibration. Across eight model--harness configurations, all 24 system runs produced valid production trajectories, yet none of the eight studies satisfied all scientific requirements. Failures included missing analyses, incorrect physical definitions or numerical implementations, insufficient statistical support, and completion claims inconsistent with retained evidence. These results expose a gap between successful MD workflow execution and reliable scientific study completion. ElectrolyteMD-Bench therefore provides a foundational test and defines a key capability threshold that autonomous electrolyte simulation must cross to advance toward computation-first materials exploration.
ER -