用闭环验证机制让大模型可靠生成高超音速隔热系统设计文件
AeroTherm-GPT: A Verification-Centered LLM Framework for Thermal Protection System Engineering Workflows
- 构建约束闭环生成框架，按工程流程迭代生成与验证
- 修复错误时优先追溯上游根源，单次修复解决4.16个下游问题
- 适合需要高可靠性工程自动化的设计团队使用
将大语言模型（LLM）融入高超音速热防护系统（TPS）设计面临生成可执行仿真文件时连锁约束违规的瓶颈。通用LLM采用单次文本补全模式，无法满足安全关键工程流程中顺序性、多级约束的要求。为此，我们提出AeroTherm-GPT，首个面向TPS的专用LLM智能体，基于约束闭环生成（CCLG）框架实现。CCLG将TPS产物生成组织为包含生成、验证、基于约束依赖图（CDG）的修复、执行与审计的迭代流程。CDG编码约束类别间的共解决结构，结合生命周期排序先验与共解决概率，指导修复优先选择上游故障源。该上游优先机制使单次操作平均解决4.16个下游违规，优于平坦检查清单修复的1.76。在HyTPS-Bench上评估并对比外部基准，AeroTherm-GPT实现88.7%的端到端成功率（95%置信区间：87.5–89.9），较未使用CDG的对照基线提升12.5个百分点，且未出现科学推理与代码生成任务的灾难性遗忘。
原文摘要 · Abstract (English)
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.
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。