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

2025-08-12

AI Summary

To address the challenge of high communication overhead and difficulty in jointly optimizing Quality of Experience (QoE) in 6G edge-assisted Mobile Augmented Reality (MAR), this paper proposes an intelligent communication service provisioning framework driven by Large Language Model (LLM)-enabled digital agents. The method establishes an edge-cooperative architecture where digital agents bridge the information gap between MAR applications and network control, enabling fine-grained, user-level QoE modeling and personalized resource scheduling. Innovatively integrating LLM-based reasoning, trajectory-driven simulation, and dynamic service adaptation, the framework significantly reduces device–edge communication load while maintaining stringent QoE requirements. Experimental results demonstrate that, compared to conventional LLM-based service approaches, the proposed method reduces QoE modeling error by 32.7% and improves communication resource utilization by 28.4%.

Technology Category

• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• Reduces communication overhead for edge-assisted mobile AR
• Bridges MAR service and network domains using LLM-powered agents
• Enables personalized QoE modeling for dynamic user traffic patterns

Innovation

• Agent-driven approach using LLMs for MAR service
• User-level QoE modeling for dynamic traffic patterns
• Edge-assisted MAR with reduced communication overhead