Interface on demand: Towards AI native Control interfaces for 6G

TL;DR

This paper introduces an AI-driven framework using large language models to dynamically generate control interfaces for 6G networks, addressing limitations of traditional static interfaces and enhancing interoperability.

Contribution

It presents a novel multi-agent system leveraging LLMs for on-demand control interface generation between network functions in 6G networks.

Findings

Validated with simulated multi-vendor environments

Analyzed cost-latency trade-offs of different LLMs

Demonstrated improved interoperability potential

Abstract

Traditional standardized network interfaces face significant limitations, including vendor-specific incompatibilities, rigid design assumptions, and lack of adaptability for new functionalities. We propose a multi-agent framework leveraging large language models (LLMs) to generate control interfaces on demand between network functions (NFs). This includes a matching agent, which aligns required control functionalities with NF capabilities, and a code-generation agent, which generates the necessary API server for interface realization. We validate our approach using simulated multi-vendor gNB and WLAN AP environments. The performance evaluations highlight the trade-offs between cost and latency across LLMs for interface generation tasks. Our work sets the foundation for AI-native dynamic control interface generation, paving the way for enhanced interoperability and adaptability in future mobile networks.