Operating LEO mega-constellations requires translating high-level operator intents ("reroute financial traffic away from polar links under 80 ms") into low-level routing constraints -- a task that demands both natural language understanding and network-domain expertise. We present an end-to-end system comprising three components: (1) a GNN cost-to-go router that distills Dijkstra-quality routing into a 152K-parameter graph attention network achieving 99.8% packet delivery ratio with 17x inference speedup; (2) an LLM intent compiler that converts natural language to a typed constraint intermediate representation using few-shot prompting with a verifier-feedback repair loop, achieving 98.4% compilation rate and 87.6% full semantic match on feasible intents in a 240-intent benchmark (193 feasible, 47 infeasible); and (3) an 8-pass deterministic validator with constructive feasibility certification that achieves 0% unsafe acceptance on all 47 infeasible intents (30 labeled + 17 discovered by Pass 8), with 100% corruption detection across 240 structural corruption tests and 100% on 15 targeted adversarial attacks. End-to-end evaluation across four constrained routing scenarios confirms zero constraint violations with both routers. We further demonstrate that apparent performance gaps in polar-avoidance scenarios are largely explained by topological reachability ceilings rather than routing quality, and that the LLM compiler outperforms a rule-based baseline by 46.2 percentage points on compositional intents. Our system bridges the semantic gap between operator intent and network configuration while maintaining the safety guarantees required for operational deployment.

翻译：运行LEO巨型星座需要将高级操作意图（例如"将金融流量重新路由，使其避开极地链路且延迟低于80毫秒"）转换为低层级路由约束——这一任务既需要自然语言理解能力，也需要网络领域专业知识。我们提出了一种端到端系统，包含三个组件：（1）一个基于图神经网络(GNN)的代价-到达路由器，将Dijkstra质量的路由方案蒸馏为一个152K参数的图注意力网络，在实现99.8%数据包投递率的同时获得17倍推理加速；（2）一个基于大语言模型(LLM)的意图编译器，利用少样本提示与验证器反馈修复循环，将自然语言转换为带类型的约束中间表示，在包含240条意图的基准测试集（其中193条可行，47条不可行）上，对可行意图实现了98.4%的编译成功率和87.6%的完整语义匹配率；（3）一个八遍确定性验证器，具备构造性可行性认证功能，对所有47条不可行意图（30条已标注+17条由第八遍发现的）实现了0%不安全通过率，在240项结构完整性测试中达到100%损坏检测率，并在15项针对性对抗攻击测试中也达到100%检测率。在四个约束路由场景上的端到端评估确认，两个路由器的零约束违规操作均得以实现。我们进一步证明，在极地规避场景中表现出的明显性能差距，很大程度上可通过拓扑可达性上限（而非路由质量）来解释，并且LLM编译器在复合意图处理上比基于规则的基线方法高出46.2个百分点。我们的系统在保障运行部署所需安全性的前提下，弥合了操作意图与网络配置之间的语义鸿沟。