---
format: "aidr-story-markdown/v1"
id: "66bc5fb5eefeedd3b98a5d10777a3d5c0aacc64a5e81a440752601513b80dbdd"
canonical_url: "https://aidr.today/66bc5fb5?lang=en"
title: "Knowledge-Guided LLM for Intent-Driven Service Orchestration in Integrated Terrestrial and Non-Terrestrial 6G Networks"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-27T04:00:00.000Z"
category: "Research"
topics: ["llm"]
source_urls: ["https://arxiv.org/abs/2610.33007"]
summary: "A knowledge-guided LLM framework is proposed for intent-driven service orchestration in integrated terrestrial and non-terrestrial 6G networks, combining grammar-constrained semantic parsing with a knowledge-graph-driven clarification loop. 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, improving on a Pure-LLM baseline."
---

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

> [Open the canonical story](<https://aidr.today/66bc5fb5?lang=en>)

**Published:** 2026-10-27T04:00:00.000Z
**Category:** Research
**Topics:** llm

## Summary

A knowledge\-guided LLM framework is proposed for intent\-driven service orchestration in integrated terrestrial and non\-terrestrial 6G networks, combining grammar\-constrained semantic parsing with a knowledge\-graph\-driven clarification loop\. 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, improving on a Pure\-LLM baseline\.

## Sources

- [Story source](<https://arxiv.org/abs/2610.33007>)