用AI生成符合物理规律的结构模型代码，让工程仿真真正可用。
Rethinking Scientific Modeling: Toward Physically Consistent and Simulation-Executable Programmatic Generation
- 构建领域知识库+约束对齐+验证闭环，确保生成代码可执行且物理正确。
- 在多个严格验证指标上优于基线，非合规输出减少78%以上。
- 适合需要高可靠建模的工程人员或自动化仿真系统开发者。
结构建模是计算工程科学的基础，微小的物理不一致或规范偏差都可能导致下游仿真失效。尽管大语言模型在自动建模代码生成方面已展现潜力，但在严苛工程约束下仍普遍存在不可执行或物理不一致的问题。为此，本文提出一个物理一致性建模框架，融合领域知识构建、面向约束的模型对齐与验证驱动的评估机制。引入CivilInstruct这一特定领域数据集，形式化结构工程知识与约束推理，实现仿真就绪的模型生成。采用两阶段微调策略，强化约束满足与API兼容性，显著降低幻觉与不合规输出。MBEval作为验证驱动的基准，通过闭环验证评估代码可执行性与结构动力学一致性。实验结果表明，在严格验证指标下各项性能均显著优于基线。代码已开源：https://github.com/Jovanqing/AutoBM。
原文摘要 · Abstract (English)
Structural modeling is a fundamental component of computational engineering science, in which even minor physical inconsistencies or specification violations may invalidate downstream simulations. The potential of large language models (LLMs) for automatic generation of modeling code has been demonstrated. However, non-executable or physically inconsistent outputs remain prevalent under stringent engineering constraints. A framework for physics-consistent automatic building modeling is therefore proposed, integrating domain knowledge construction, constraint-oriented model alignment, and verification-driven evaluation. CivilInstruct is introduced as a domain-specific dataset that formalizes structural engineering knowledge and constraint reasoning to enable simulation-ready model generation. A two-stage fine-tuning strategy is further employed to enforce constraint satisfaction and application programming interface compliance, substantially reducing hallucinated and non-conforming outputs. MBEval is presented as a verification-driven benchmark that evaluates executability and structural dynamics consistency through closed-loop validation. Experimental results show consistent improvements over baselines across rigorous verification metrics. Our code is available at https://github.com/Jovanqing/AutoBM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。