Saved in:
Bibliographic Details
Main Authors: Petković, Marko, Menkovski, Vlado, Calero, Sofía
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.10210
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915491902128128
author Petković, Marko
Menkovski, Vlado
Calero, Sofía
author_facet Petković, Marko
Menkovski, Vlado
Calero, Sofía
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2509_10210
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Fully Automated Molecular Simulations: Multi-Agent Framework for Simulation Setup and Force Field Extraction
Petković, Marko
Menkovski, Vlado
Calero, Sofía
Artificial Intelligence
Multiagent Systems
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.
title Towards Fully Automated Molecular Simulations: Multi-Agent Framework for Simulation Setup and Force Field Extraction
topic Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2509.10210