PulseAugur
实时 20:23:45
None LLM-driven design of physics-constrained constitutive models: two agents are better than one

LLM通过双智能体系统创建符合物理规律的材料模型

研究人员开发了一种新颖的多智能体系统,利用大型语言模型生成物理约束本构模型。该方法采用“创建者”智能体提出模型,并由“检查者”智能体根据九个物理约束对其进行严格审计,确保其有效性。该系统在物理上合理的模型比例方面显示出显著的改进,Claude Opus 4.7 达到了 100%,Kimi K2.5 达到了 56%,同时保持了准确性和泛化能力。 AI

影响 实现对物理上有效且准确的材料模型的自动化发现,加速科学研究和工程应用。

排序理由 该集群包含一篇学术论文,详细介绍了使用 LLM 进行科学模型生成的新方法。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

报道来源 [2]

  1. arXiv cs.LG TIER_1 · Marius Tacke, Matthias Busch, Kian Abdolazizi, Jonas Eichinger, Kevin Linka, Roland Aydin, Christian Cyron ·

    LLM-driven design of physics-constrained constitutive models: two agents are better than one

    arXiv:2605.23754v1 Announce Type: new Abstract: Developing constitutive models that capture how materials deform under load traditionally requires years of specialized expertise in continuum mechanics, machine learning, and scientific programming. Large language models (LLMs) hav…

  2. arXiv cs.LG TIER_1 · Christian Cyron ·

    LLM-driven design of physics-constrained constitutive models: two agents are better than one

    Developing constitutive models that capture how materials deform under load traditionally requires years of specialized expertise in continuum mechanics, machine learning, and scientific programming. Large language models (LLMs) have recently been shown to lower this barrier by g…