LLM-Empowered Agentic AI for QoE-Aware Network Slicing Management in Industrial IoT

TL;DR

This paper proposes an LLM-empowered agentic AI framework for QoE-aware network slicing in IIoT, combining reasoning, planning, and adaptation to improve network performance under dynamic conditions.

Contribution

It introduces an integrated LLM-based agentic AI approach with RAG, DRL, and memory mechanisms for dynamic network slicing management in IIoT environments.

Findings

Achieves up to 19% improvement in slice availability ratio.

Significantly outperforms baseline methods in balancing latency, reliability, and cost.

Demonstrates effective continual learning and semantic intent inference.

Abstract

The Industrial Internet of Things (IIoT) requires networks that deliver ultra-low latency, high reliability, and cost efficiency, which traditional optimization methods and deep reinforcement learning (DRL)-based approaches struggle to provide under dynamic and heterogeneous workloads. To address this gap, large language model (LLM)-empowered agentic AI has emerged as a promising paradigm, integrating reasoning, planning, and adaptation to enable QoE-aware network management. In this paper, we explore the integration of agentic AI into QoE-aware network slicing for IIoT. We first review the network slicing management architecture, QoE metrics for IIoT applications, and the challenges of dynamically managing heterogeneous network slices, while highlighting the motivations and advantages of adopting agentic AI. We then present the workflow of agentic AI-based slicing management, illustrating the full lifecycle of AI agents from processing slice requests to constructing slice instances and performing dynamic adjustments. Furthermore, we propose an LLM-empowered agentic AI approach for slicing management, which integrates a retrieval-augmented generation (RAG) module for semantic intent inference, a DRL-based orchestrator for slicing configuration, and an incremental memory mechanism for continual learning and adaptation. Through a case study on heterogeneous slice management, we demonstrate that the proposed approach significantly outperforms other baselines in balancing latency, reliability, and cost, and achieves up to a 19% improvement in slice availability ratio.