Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2604.01738 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912998114721792 |
|---|---|
| author | Qiao, Chuhan Zheng, Jinglai Huang, Jie Zhao, Buyue Li, Fan Huang, Haiming |
| author_facet | Qiao, Chuhan Zheng, Jinglai Huang, Jie Zhao, Buyue Li, Fan Huang, Haiming |
| contents | Integrating Large Language Models (LLMs) into hypersonic thermal protection system (TPS) design is bottlenecked by cascading constraint violations when generating executable simulation artifacts. General-purpose LLMs, treating generation as single-pass text completion, fail to satisfy the sequential, multi-gate constraints inherent in safety-critical engineering workflows. To address this, we propose AeroTherm-GPT, the first TPS-specialized LLM Agent, instantiated through a Constraint-Closed-Loop Generation (CCLG) framework. CCLG organizes TPS artifact generation as an iterative workflow comprising generation, validation, CDG-guided repair, execution, and audit. The Constraint Dependency Graph (CDG) encodes empirical co-resolution structure among constraint categories, directing repair toward upstream fault candidates based on lifecycle ordering priors and empirical co-resolution probabilities. This upstream-priority mechanism resolves multiple downstream violations per action, achieving a Root-Cause Fix Efficiency of 4.16 versus 1.76 for flat-checklist repair. Evaluated on HyTPS-Bench and validated against external benchmarks, AeroTherm-GPT achieves 88.7% End-to-End Success Rate (95% CI: 87.5-89.9), a gain of +12.5 pp over the matched non-CDG ablation baseline, without catastrophic forgetting on scientific reasoning and code generation tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_01738 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AeroTherm-GPT: A Verification-Centered LLM Framework for Thermal Protection System Engineering Workflows Qiao, Chuhan Zheng, Jinglai Huang, Jie Zhao, Buyue Li, Fan Huang, Haiming Artificial Intelligence Integrating Large Language Models (LLMs) into hypersonic thermal protection system (TPS) design is bottlenecked by cascading constraint violations when generating executable simulation artifacts. General-purpose LLMs, treating generation as single-pass text completion, fail to satisfy the sequential, multi-gate constraints inherent in safety-critical engineering workflows. To address this, we propose AeroTherm-GPT, the first TPS-specialized LLM Agent, instantiated through a Constraint-Closed-Loop Generation (CCLG) framework. CCLG organizes TPS artifact generation as an iterative workflow comprising generation, validation, CDG-guided repair, execution, and audit. The Constraint Dependency Graph (CDG) encodes empirical co-resolution structure among constraint categories, directing repair toward upstream fault candidates based on lifecycle ordering priors and empirical co-resolution probabilities. This upstream-priority mechanism resolves multiple downstream violations per action, achieving a Root-Cause Fix Efficiency of 4.16 versus 1.76 for flat-checklist repair. Evaluated on HyTPS-Bench and validated against external benchmarks, AeroTherm-GPT achieves 88.7% End-to-End Success Rate (95% CI: 87.5-89.9), a gain of +12.5 pp over the matched non-CDG ablation baseline, without catastrophic forgetting on scientific reasoning and code generation tasks. |
| title | AeroTherm-GPT: A Verification-Centered LLM Framework for Thermal Protection System Engineering Workflows |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.01738 |