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 2311.08166cs.AIcond-mat.dis-nncond-mat.mtrl-scics.CLcs.LG
收藏

MechAgents:大语言模型多智能体协作能够解决力学问题、生成新数据并整合知识

MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledge

Massachusetts Institute of Technology(麻省理工学院);Schwarzman College of Computing(计算学院(施瓦曼学院))

Bo Ni, Markus J. Buehler

AI总结:

本文提出MechAgents框架,利用多个大语言模型智能体动态协作,通过自主编写、执行和自纠错代码求解弹性力学问题,并生成新数据与整合知识,展示了物理建模与AI协同的自动化潜力。

摘要:

使用数值方法求解力学问题需要具备检索相关知识理论、构建并执行代码、分析结果的综合智能能力,这一任务迄今主要仍由人类承担。虽然新兴的人工智能方法可以提供解决端到端问题的有效途径,例如通过使用深度代理模型或各种数据分析策略,但它们往往缺乏物理直觉,因为知识是通过训练嵌入到参数化补充中的,在纳入数学或物理见解方面灵活性较低。通过利用多个动态交互的大语言模型(LLM)的多样化能力,我们可以克服传统方法的局限性,并开发一类新的物理启发的生成式机器学习平台,此处称为MechAgents。一组AI智能体可以通过自主协作解决力学任务,此处以弹性问题为例进行演示。一个双智能体团队能够有效地编写、执行和自纠错代码,以应用有限元方法求解各种形式的经典弹性问题(不同边界条件、域几何、网格、小/有限变形和线性/超弹性本构定律等)。对于更复杂的任务,我们构建了一个更大的智能体组,在规划、制定、编码、执行以及批判过程和结果之间增强了分工。这些智能体相互纠正,以提高整个团队在理解、制定和验证解决方案方面的协作表现。我们的框架展示了协同语言模型智能、基于物理建模的可靠性以及不同智能体间动态协作的潜力,为工程问题求解的自动化开辟了新途径。

英文摘要:

Solving mechanics problems using numerical methods requires comprehensive intelligent capability of retrieving relevant knowledge and theory, constructing and executing codes, analyzing the results, a task that has thus far mainly been reserved for humans. While emerging AI methods can provide effective approaches to solve end-to-end problems, for instance via the use of deep surrogate models or various data analytics strategies, they often lack physical intuition since knowledge is baked into the parametric complement through training, offering less flexibility when it comes to incorporating mathematical or physical insights. By leveraging diverse capabilities of multiple dynamically interacting large language models (LLMs), we can overcome the limitations of conventional approaches and develop a new class of physics-inspired generative machine learning platform, here referred to as MechAgents. A set of AI agents can solve mechanics tasks, here demonstrated for elasticity problems, via autonomous collaborations. A two-agent team can effectively write, execute and self-correct code, in order to apply finite element methods to solve classical elasticity problems in various flavors (different boundary conditions, domain geometries, meshes, small/finite deformation and linear/hyper-elastic constitutive laws, and others). For more complex tasks, we construct a larger group of agents with enhanced division of labor among planning, formulating, coding, executing and criticizing the process and results. The agents mutually correct each other to improve the overall team-work performance in understanding, formulating and validating the solution. Our framework shows the potential of synergizing the intelligence of language models, the reliability of physics-based modeling, and the dynamic collaborations among diverse agents, opening novel avenues for automation of solving engineering problems.

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。

↑