QoE-Aware Service Provision for Mobile AR Rendering: An Agent-Driven Approach

TL;DR

This paper introduces an agent-driven approach using large language models to optimize communication services for mobile AR, reducing overhead while maintaining high user QoE in edge-assisted environments.

Contribution

It presents a novel agent-powered framework that bridges MAR and network domains and models user QoE for personalized resource management.

Findings

Outperforms traditional methods in QoE modeling accuracy

Reduces communication overhead effectively

Enhances user experience in mobile AR applications

Abstract

Mobile augmented reality (MAR) is envisioned as a key immersive application in 6G, enabling virtual content rendering aligned with the physical environment through device pose estimation. In this paper, we propose a novel agent-driven communication service provisioning approach for edge-assisted MAR, aiming to reduce communication overhead between MAR devices and the edge server while ensuring the quality of experience (QoE). First, to address the inaccessibility of MAR application-specific information to the network controller, we establish a digital agent powered by large language models (LLMs) on behalf of the MAR service provider, bridging the data and function gap between the MAR service and network domains. Second, to cope with the user-dependent and dynamic nature of data traffic patterns for individual devices, we develop a user-level QoE modeling method that captures the relationship between communication resource demands and perceived user QoE, enabling personalized, agent-driven communication resource management. Trace-driven simulation results demonstrate that the proposed approach outperforms conventional LLM-based QoE-aware service provisioning methods in both user-level QoE modeling accuracy and communication resource efficiency.