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

2025-09-12

AI Summary

Automated molecular simulation of porous materials is hindered by the complexity of simulation setup and heavy reliance on manual force-field parameterization. Method: This paper introduces the first large language model (LLM)-driven multi-agent collaborative framework for end-to-end automation of porous material characterization—enabling autonomous extraction of force-field parameters from literature, automatic configuration, execution, and analysis of RASPA simulations. The system integrates natural language understanding, hierarchical task planning, and seamless orchestration of simulation toolchains. Contribution/Results: Preliminary evaluation demonstrates high accuracy in parameter extraction, correctness of generated input files, and reproducibility of simulations. By eliminating expert intervention traditionally required at multiple stages, the framework significantly accelerates high-throughput screening and discovery of porous materials.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Automating porous materials simulation setup complexity
• Addressing force field selection challenges in simulations
• Enabling autonomous multi-agent molecular simulation workflows

Innovation

• Multi-agent framework automates simulation setup
• LLM-based agents autonomously plan and execute simulations
• Automated force field extraction from scientific literature