AutoNumerics: 一种自主的、与偏微分方程无关的多智能体流水线用于科学计算
AutoNumerics: An Autonomous, PDE-Agnostic Multi-Agent Pipeline for Scientific Computing
AI总结:
AutoNumerics通过多智能体框架自主设计并验证数值求解器,基于自然语言描述实现高效准确的偏微分方程求解。
摘要:
偏微分方程是科学和工程建模的核心,但设计准确的数值求解器通常需要大量的数学专业知识和手动调整。最近的基于神经网络的方法提高了灵活性,但通常需要高昂的计算成本,并且存在有限的可解释性。我们介绍了AutoNumerics,一种多智能体框架,能够自主地为一般的偏微分方程设计、实现、调试和验证数值求解器,直接从自然语言描述中获取。与黑盒神经求解器不同,我们的框架生成基于经典数值分析的透明求解器。我们引入了一种粗到细的执行策略和基于残差的自验证机制。在24个标准和现实世界偏微分方程问题上的实验表明,AutoNumerics在准确性上与现有神经网络和大语言模型基线相比具有竞争力或更优,并且能够根据偏微分方程的结构特性正确选择数值方案,表明其作为自动化偏微分方程求解的可行范式。
英文摘要:
PDEs are central to scientific and engineering modeling, yet designing accurate numerical solvers typically requires substantial mathematical expertise and manual tuning. Recent neural network-based approaches improve flexibility but often demand high computational cost and suffer from limited interpretability. We introduce \texttt{AutoNumerics}, a multi-agent framework that autonomously designs, implements, debugs, and verifies numerical solvers for general PDEs directly from natural language descriptions. Unlike black-box neural solvers, our framework generates transparent solvers grounded in classical numerical analysis. We introduce a coarse-to-fine execution strategy and a residual-based self-verification mechanism. Experiments on 24 canonical and real-world PDE problems demonstrate that \texttt{AutoNumerics} achieves competitive or superior accuracy compared to existing neural and LLM-based baselines, and correctly selects numerical schemes based on PDE structural properties, suggesting its viability as an accessible paradigm for automated PDE solving.
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。