Towards Fully Automated Molecular Simulations: Multi-Agent Framework for Simulation Setup and Force Field Extraction

Marko Petković, Vlado Menkovski, Sofia Calero

Keywords: Agentic AI, Molecular Simulation, Automated Characterization

TL;DR: We introduce a multi-agent LLM system that autonomously plans, executes, and evaluates simulations for materials characterization, showing promising initial results for zeolite adsorption and force field extraction.

Abstract: Automated characterization of porous materials has the potential to accelerate materials discovery, but it remains limited by the complexity of simulation setup and force field selection. We propose a multi-agent framework in which LLM-based agents can autonomously understand a characterization task, plan appropriate simulations, assemble relevant force fields, execute them and interpret their results to guide subsequent steps. As a first step toward this vision, we present a multi-agent system for literature-informed force field extraction and automated RASPA simulation setup. Initial evaluations demonstrate high correctness and reproducibility, highlighting this approach’s potential to enable fully autonomous, scalable materials characterization.

Submission Track: Paper Track (Short Paper)

Submission Category: Automated Material Characterization

Institution Location: Eindhoven, Netherlands

AI4Mat RLSF: Yes

Submission Number: 141