Knowledge-Guided LLM for Intent-Driven Service Orchestration in Integrated Terrestrial and Non-Terrestrial 6G Networks

Computer Science > Computation and Language arXiv:2610.33007 (cs) [Submitted on 7 Oct 2026] Title: Knowledge-Guided LLM for Intent-Driven Service Orchestration in Integrated Terrestrial and Non-Terrestrial 6G Networks Authors: Wajdi Hammami, Irfan Azam, Soumaya Cherkaoui.

计算机科学 > 计算与语言 arXiv:2610.33007 (cs) [提交于 2026 年 10 月 7 日] 标题：面向集成地面与非地面 6G 网络中意图驱动服务编排的知识引导大语言模型 作者：Wajdi Hammami, Irfan Azam, Soumaya Cherkaoui。

Abstract: Natural-language service intents in integrated terrestrial and non-terrestrial (TN/NTN) 6G networks can be incomplete, ambiguous, or inconsistent, making unconstrained LLM generation challenging for reliable network-facing orchestration.

摘要：在集成地面与非地面 (TN/NTN) 6G 网络中，自然语言服务意图可能存在不完整、模棱两可或不一致的情况，这使得无约束的大语言模型生成难以实现可靠的网络编排。

This paper proposes a knowledge-guided LLM framework that combines grammar-constrained semantic parsing with a knowledge-graph (KG)-driven clarification loop to produce validated, orchestration-ready service profiles across four representative service classes.

本文提出了一种知识引导的大语言模型框架，该框架结合了语法约束语义解析与知识图谱 (KG) 驱动的澄清循环，旨在为四类代表性服务生成经过验证且可直接用于编排的服务配置文件。

On a 200-sample intent dataset, the framework achieves 89% classification accuracy and 95% policy validity with an average of 0.66 clarification turns per request.

在包含 200 个样本的意图数据集上，该框架实现了 89% 的分类准确率和 95% 的策略有效性，且平均每个请求仅需 0.66 次澄清交互。

Compared with a Pure-LLM baseline, the proposed framework improves policy validity and contradiction detection while requiring fewer clarification turns, demonstrating the value of explicit knowledge-guided reasoning for robust intent processing in integrated TN/NTN 6G orchestration.

与纯大语言模型基准相比，该框架提高了策略有效性和矛盾检测能力，同时减少了澄清交互次数，证明了显式知识引导推理在集成 TN/NTN 6G 编排中进行稳健意图处理的价值。