MDCrow: Automating Molecular Dynamics Workflows with Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Campbell, Quintina, Cox, Sam, Medina, Jorge, Watterson, Brittany, White, Andrew D.
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913689757548544
author Campbell, Quintina
Cox, Sam
Medina, Jorge
Watterson, Brittany
White, Andrew D.
author_facet Campbell, Quintina
Cox, Sam
Medina, Jorge
Watterson, Brittany
White, Andrew D.
contents Molecular dynamics (MD) simulations are essential for understanding biomolecular systems but remain challenging to automate. Recent advances in large language models (LLM) have demonstrated success in automating complex scientific tasks using LLM-based agents. In this paper, we introduce MDCrow, an agentic LLM assistant capable of automating MD workflows. MDCrow uses chain-of-thought over 40 expert-designed tools for handling and processing files, setting up simulations, analyzing the simulation outputs, and retrieving relevant information from literature and databases. We assess MDCrow's performance across 25 tasks of varying required subtasks and difficulty, and we evaluate the agent's robustness to both difficulty and prompt style. \texttt{gpt-4o} is able to complete complex tasks with low variance, followed closely by \texttt{llama3-405b}, a compelling open-source model. While prompt style does not influence the best models' performance, it has significant effects on smaller models.
format Preprint
id arxiv_https___arxiv_org_abs_2502_09565
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MDCrow: Automating Molecular Dynamics Workflows with Large Language Models
Campbell, Quintina
Cox, Sam
Medina, Jorge
Watterson, Brittany
White, Andrew D.
Artificial Intelligence
Chemical Physics
Molecular dynamics (MD) simulations are essential for understanding biomolecular systems but remain challenging to automate. Recent advances in large language models (LLM) have demonstrated success in automating complex scientific tasks using LLM-based agents. In this paper, we introduce MDCrow, an agentic LLM assistant capable of automating MD workflows. MDCrow uses chain-of-thought over 40 expert-designed tools for handling and processing files, setting up simulations, analyzing the simulation outputs, and retrieving relevant information from literature and databases. We assess MDCrow's performance across 25 tasks of varying required subtasks and difficulty, and we evaluate the agent's robustness to both difficulty and prompt style. \texttt{gpt-4o} is able to complete complex tasks with low variance, followed closely by \texttt{llama3-405b}, a compelling open-source model. While prompt style does not influence the best models' performance, it has significant effects on smaller models.
title MDCrow: Automating Molecular Dynamics Workflows with Large Language Models
topic Artificial Intelligence
Chemical Physics
url https://arxiv.org/abs/2502.09565