Customized User Plane Processing via Code Generating AI Agents for Next Generation Mobile Networks

TL;DR

This paper explores using generative AI agents to create customized user plane processing code for 6G networks, enabling on-demand network-specific functionality.

Contribution

It investigates the code generation process for network tasks, analyzing factors affecting accuracy and demonstrating AI agents' capability to generate desired code blocks.

Findings

AI agents can generate network processing code with desired behavior under suitable conditions.

Model selection, prompt design, and code templates significantly affect code generation accuracy.

On-demand code generation enables flexible, customized network functionalities for 6G.

Abstract

Generative AI is envisioned to have a crucial impact on next generation mobile networking, making the sixth generation (6G) system considerably more autonomous, flexible, and adaptive than its predecessors. By leveraging their natural language processing and code generation capabilities, AI agents enable novel interactions and services between networks and vertical applications. A particularly promising and interesting use case is the customization of connectivity services for vertical applications by generating new customized processing blocks based on text-based service requests. More specifically, AI agents are able to generate code for a new function block that handles user plane traffic, allowing it to inspect and decode a protocol data unit (PDU) and perform specified actions as requested by the application. In this study, we investigate the code generation problem for generating such customized processing blocks on-demand. We evaluate various factors affecting the accuracy of the code generation process in this context, including model selection, prompt design, and the provision of a code template for the agent to utilize. Our findings indicate that AI agents are capable of generating such blocks with the desired behavior on-demand under suitable conditions. We believe that exploring the code generation for network-specific tasks is a very interesting problem for 6G and beyond, enabling networks to achieve a new level of customization by generating new capabilities on-demand.