物理审计的智能体发现在科学机器学习中的应用
Physics-Audited Agentic Discovery in Scientific Machine Learning
Diab W. Abueidda · Bilal Ahmed · Panos Pantidis · Mostafa E. Mobasher
中文摘要
智能体发现可能产生验证误差低但违反物理要求的力学代理模型。提出 Physics-Audited Agentic SciML（PA-SciML）框架，将大语言模型智能体与物理审计结合。物理要求以叠加性、边界条件和因果性等契约形式在候选搜索前固定，并在无参考解情况下对预测场进行测试，包括对抗性搜索。审计结果指导后续提案和模型选择，但与验证误差分开报告。单编辑测试记录可复用的设计变更。四个复杂度递增的固体力学问题——从参数化弹性到非均匀刚度场及组合硬化的循环塑性——揭示了仅按误差选择的代理模型存在因果性、零输入和应力边界违反。在弹性动力学中，两个代理模型达到几乎相等的误差，但只有启用审计的模型在构造上满足因果性。启用审计的代理模型在采样输入上通过所需检查，同时在多数比较中匹配或超过禁用审计的精度。
关键要点
- 01仅按验证误差选择的代理模型可能违反因果性、零输入和应力边界等物理要求。
- 02PA-SciML 在搜索前固定物理契约，无需参考解即可审计预测场并指导模型选择。
- 03四个固体力学问题显示审计结果与验证误差需分开报告，单编辑测试可记录可复用设计变更。
- 04弹性动力学中两个代理误差相近，但仅审计启用的模型在构造上满足因果性。
- 05审计启用的代理在采样输入通过检查，多数比较中精度匹配或超过未审计版本。
解读
尚无解读。
原始英文摘要
arXiv:2607.07379v2 Announce Type: replace Abstract: Agentic discovery can yield mechanics surrogates with low validation error that nonetheless violate physical requirements. We present Physics-Audited Agentic SciML (PA-SciML), a framework combining large language model agents with physics auditing. Physical requirements, encoded as contracts such as superposition, boundary conditions, and causality, are fixed before candidate search and tested on predicted fields without reference solutions, including through an adversarial search. Audit results guide later proposals and model selection but are reported separately from validation error. Single-edit tests document reusable design changes. Four solid-mechanics problems of increasing complexity, from parametric elasticity to heterogeneous stiffness fields and cyclic plasticity with combined hardening, reveal causality, zero-input, and stress-bound violations in surrogates selected by error alone. In elastodynamics, two surrogates reach nearly equal error, but only the audit-enabled one is causal by construction. Audit-enabled surrogates pass the required checks at sampled inputs while matching or exceeding audit-disabled accuracy in most comparisons.