Toward 6G edge intelligence: Lightweight LLMs for intent-driven network automation
Author Identifier (ORCID)
Abstract
Future 6 G networks are envisaged to tightly integrate communication, sensing, and computing, demanding real-time, intent-driven intelligence at the edge. While large language models (LLMs) excel in intent recognition and semantic reasoning, their application to real-time network lifecycle management at the edge is limited by heterogeneous application intents (APPIs), dynamic network conditions, and severe resource constraints. This paper proposes a novel lightweight LLM architecture, KGLlama-KD, that synergizes knowledge graphs (KGs) with knowledge distillation (KD) to enable intent-driven networking and enhance 6 G edge intelligence. Specifically, a KG is constructed to formally describe the relationships among application scenarios, functional primitives, performance requirements within APPIs, and the correspondences between APPIs and network service requests (NSRs), thereby producing a structured intent training dataset. Building upon the Llama 3 foundation model, a two-phase optimization framework is designed to support lightweight edge deployment while preserving translation fidelity. The LLM is first fine-tuned with KG guidance and compressed via KD in the cloud, and then deployed on resource-constrained edge nodes to perform real-time, accurate, and efficient APPIs interpretation. Experiments validate that KGLlama-KD achieves 95% accuracy for APPI understanding, surpassing DeepSeek and Qwen by an average of 8%. The distilled model reduces inference latency by 60% compared to full-scale LLMs, fulfilling the sub-100 ms requirement for 6 G latency-sensitive services.
Keywords
6 G edge intelligence, application intent, knowledge distillation, knowledge graph, large language model, network service request
Document Type
Journal Article
Date of Publication
1-1-2026
Publication Title
IEEE Transactions on Mobile Computing
Publisher
IEEE
School
School of Engineering
Funders
National Research and Development Programs of China (2025YFB3109801) / National Natural Science Foundation of China (62361011, U24A20246, 62271424) / Guizhou Provincial Science and Technology Plan Project (DXGA[2025]003, DXGA[2025]011) / Guizhou Province Scientist Workstation (KXJZ[2025]005) / Guizhou Province Science and Technology Innovation Platform (JSZX(2025)020)
Copyright
subscription content
Comments
Wu, B., Zou, S., Liwang, M., Ni, W., Wang, X., & Tian, Y. (2026). Toward 6G edge intelligence: Lightweight LLMs for intent-driven network automation. IEEE Transactions on Mobile Computing. Advance online publication. https://doi.org/10.1109/TMC.2026.3678546