arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2604.01738cs.AI
收藏

AeroTherm-GPT:一种面向热防护系统工程工作流的验证中心LLM框架

AeroTherm-GPT: A Verification-Centered LLM Framework for Thermal Protection System Engineering Workflows

School of Civil Engineering, Beijing Jiaotong University(北京交通大学土木工程学院);Beijing Research Institute of Telemetry(北京遥测技术研究所)

Chuhan Qiao, Jinglai Zheng, Jie Huang, Buyue Zhao, Fan Li, Haiming Huang

AI总结:

本文提出AeroTherm-GPT,一种专为热防护系统设计的LLM代理,通过约束闭环生成框架解决超音速热防护系统设计中生成可执行仿真工具时的约束冲突问题,实现高效率的根因修复。

摘要:

将大型语言模型(LLMs)集成到高超音速热防护系统(TPS)设计中受到生成可执行仿真工具时连续约束违反的瓶颈限制。通用LLMs将生成视为单次文本完成,无法满足安全关键工程工作流中固有的顺序、多门约束。为此,我们提出了AeroTherm-GPT,首个专为TPS设计的LLM代理,通过约束闭环生成(CCLG)框架实现。CCLG将TPS工具生成组织为包含生成、验证、CDG引导修复、执行和审计的迭代工作流。约束依赖图(CDG)编码了约束类别的经验共解结构,根据生命周期顺序优先级和经验共解概率指导修复上游故障候选者。这种上游优先机制每次操作可解决多个下游违规,实现根因修复效率为4.16,而非扁平检查表修复的1.76。在HyTPS-Bench上评估并在外部基准上验证,AeroTherm-GPT实现了88.7%的端到端成功率(95%置信区间:87.5-89.9),比匹配的非CDG消融基线高出+12.5个百分点,且在科学推理和代码生成任务上无灾难性遗忘。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑