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 2408.15512cs.AIcs.CLphysics.chem-ph
收藏

通过大语言模型提示工程设计实现自动化模拟研究工作流

Toward Automated Simulation Research Workflow through LLM Prompt Engineering Design

Zhihan Liu, Yubo Chai, Jianfeng Li

AI总结:

本研究通过提示工程构建由大语言模型驱动的自主模拟智能体(ASA),可自动完成模拟研究全流程,经聚合物链构象问题测试,GPT-4o驱动的ASA表现优异,可无人工干预迭代20周期,为提升科研效率提供新路径。

摘要:

大语言模型(LLM)的出现为横跨实验流程与计算模拟的科学研究自动化创造了新机遇。本研究探讨了通过提示工程与自动化程序设计,构建由LLM驱动的自主模拟智能体(autonomous simulation agent, ASA),以根据人类提供的研究计划自动化完成整个模拟研究流程的可行性。该流程涵盖实验设计、远程上传与模拟执行、数据分析及报告撰写。我们以一个已被充分研究的聚合物链构象模拟问题作为测试用例,评估了由GPT-4o、Claude-3.5等不同LLM驱动的ASA的长任务完成能力与可靠性。研究结果显示,ASA-GPT-4o在指定研究任务中实现了近乎完美的执行,凸显了ASA这类方法在模拟研究流程中实现自动化、提升研究效率的潜力。上述自动化流程可在无需人工干预的情况下迭代执行多达20个周期,证明了ASA在长任务工作流自动化方面的潜力。此外,我们还讨论了ASA在处理大规模任务时的内在特性,重点关注自验证机制,以及局部注意力与全局监督之间的平衡。

英文摘要:

The advent of Large Language Models (LLMs) has created new opportunities for the automation of scientific research spanning both experimental processes and computational simulations. This study explores the feasibility of constructing an autonomous simulation agent (ASA) powered by LLMs through prompt engineering and automated program design to automate the entire simulation research process according to a human-provided research plan. This process includes experimental design, remote upload and simulation execution, data analysis, and report compilation. Using a well-studied simulation problem of polymer chain conformations as a test case, we assessed the long-task completion and reliability of ASAs powered by different LLMs, including GPT-4o, Claude-3.5, etc. Our findings revealed that ASA-GPT-4o achieved near-flawless execution on designated research missions, underscoring the potential of methods like ASA to achieve automation in simulation research processes to enhance research efficiency. The outlined automation can be iteratively performed for up to 20 cycles without human intervention, illustrating the potential of ASA for long-task workflow automation. Additionally, we discussed the intrinsic traits of ASA in managing extensive tasks, focusing on self-validation mechanisms, and the balance between local attention and global oversight.

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。

↑