用大模型与小模型协同实现5G/6G网络自主编排，提速20%。
Performance Comparison of IBN orchestration using LLM and SLMs
- 构建分层有状态多智能体架构，融合LLM与SLM实现自动编排。
- 两者翻译准确率相近，但小模型使网络生命周期完成速度提升20%。
- 适合关注网络自动化与推理效率的通信系统研究人员。
5G和6G网络的发展正推动全自治网络管理的演进，意图驱动网络（IBN）成为这一变革的核心。本文提出一种新颖的5G/6G IBN编排框架，采用有状态、分层的多智能体架构，利用大型语言模型（LLM）和小型语言模型（SLM）实现全流程自动化。通过BLEU、METEOR和ROUGE-L等指标评估了两种模型在翻译准确率方面的表现，同时对比了计算复杂度。实验结果表明，两种模型在准确率上表现相当，但SLMs可将IBN生命周期的整体完成速度提升20%。
原文摘要 · Abstract (English)
The evolution of both 5G and 6G networks is driving the advancement of fully autonomous network management, placing Intent-Based Networking at the centre of this transformation. This paper introduces a novel framework for 5G and 6G IBN orchestration that leverages a stateful, hierarchical multi-agent architecture to achieve full automation using both SLMs and LLMs. Both models have been evaluated for translation accuracy using metrics such as BLEU, METEOR, and ROUGE-L, as well as computational complexity. Experimental results show that both models exhibit similar accuracy. However, result shows that SLMs can improve the overall completion speed of the IBN lifecycle by 20%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。