{"slug": "knowledge-guided-llm-for-intent-driven-service-orchestration-in-integrated-and", "title": "Knowledge-Guided LLM for Intent-Driven Service Orchestration in Integrated Terrestrial and Non-Terrestrial 6G Networks", "summary": "A knowledge-guided LLM framework combining grammar-constrained semantic parsing with a knowledge-graph-driven clarification loop achieved 89% classification accuracy and 95% policy validity on a 200-sample intent dataset for service orchestration in integrated terrestrial and non-terrestrial 6G networks, according to an arXiv paper (arXiv:2610.33007v1). The framework averaged 0.66 clarification turns per request and, compared with a Pure-LLM baseline, improved policy validity and contradiction detection while requiring fewer clarification turns, the authors report. The work targets natural-language service intents that can be incomplete, ambiguous, or inconsistent, producing validated, orchestration-ready service profiles across four representative service classes.", "body_md": "arXiv:2610.33007v1 Announce Type: new \nAbstract: 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. 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. 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. 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.", "url": "https://wpnews.pro/news/knowledge-guided-llm-for-intent-driven-service-orchestration-in-integrated-and", "canonical_source": "https://arxiv.org/abs/2610.33007", "published_at": "2026-10-27 04:00:00+00:00", "updated_at": "2026-10-27 04:11:58.606002+00:00", "lang": "en", "topics": ["large-language-models", "natural-language-processing", "artificial-intelligence", "ai-research"], "entities": ["arXiv", "Pure-LLM"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/knowledge-guided-llm-for-intent-driven-service-orchestration-in-integrated-and", "markdown": "https://wpnews.pro/news/knowledge-guided-llm-for-intent-driven-service-orchestration-in-integrated-and.md", "text": "https://wpnews.pro/news/knowledge-guided-llm-for-intent-driven-service-orchestration-in-integrated-and.txt", "jsonld": "https://wpnews.pro/news/knowledge-guided-llm-for-intent-driven-service-orchestration-in-integrated-and.jsonld"}}