arXiv cs.AI· Diab W. Abueidda, Bilal Ahmed, Panos Pantidis, Mostafa E. Mobasher·· 11 小时前AI 评分38
PA-SciML：用物理审计约束 LLM 智能体的科学机器学习发现
Physics-Audited Agentic Discovery in Scientific Machine Learning
AI 导读
研究者提出 Physics-Audited Agentic SciML（PA-SciML）框架，将 LLM 智能体与物理审计结合，在候选搜索前把叠加性、边界条件、因果性等物理要求固化为契约，并在无参考解的情况下对预测场做对抗性检验。
正文 · 原文
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.
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG) |
| Cite as: | arXiv:2607.07379 [cs.AI] |
| (or arXiv:2607.07379v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.07379 arXiv-issued DOI via DataCite |
Submission history
From: Mostafa Mobasher [view email]
[v1]
Wed, 8 Jul 2026 13:10:35 UTC (3,438 KB)
[v2]
Fri, 30 Oct 2026 11:21:04 UTC (5,193 KB)
来源：arXiv cs.AI · arxiv.org