arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.09565cs.AIphysics.chem-ph
收藏

MDCrow:利用大语言模型自动化分子动力学工作流

MDCrow: Automating Molecular Dynamics Workflows with Large Language Models

University of Rochester(罗切斯特大学);FutureHouse Inc.(FutureHouse公司)

Quintina Campbell, Sam Cox, Jorge Medina, Brittany Watterson, Andrew D. White

AI总结:

针对分子动力学模拟自动化的挑战,本文提出智能体式LLM助手MDCrow,通过思维链调用40个专家工具实现MD工作流自动化,在25个任务中评估显示gpt-4o和llama3-405b表现优异,提示风格对小模型影响显著。

摘要:

分子动力学(MD)模拟对于理解生物分子系统至关重要,但自动化仍具挑战。大语言模型(LLM)的最新进展已证明,基于LLM的智能体可成功自动化复杂科学任务。本文介绍MDCrow,这是一种能自动化MD工作流的智能体式LLM助手。MDCrow通过思维链调用40个专家设计的工具,用于文件处理与加工、模拟设置、模拟输出分析,以及从文献和数据库中检索相关信息。我们在25个具有不同子任务需求和难度的任务中评估MDCrow的性能,并评估智能体对难度和提示风格的鲁棒性。\texttt{gpt-4o}能以低方差完成复杂任务,紧随其后的是极具竞争力的开源模型\texttt{llama3-405b}。提示风格不影响最优模型的性能,但对较小模型有显著影响。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑