QoEReasoner: An Agentic Reasoning Framework for Automated and Explainable QoE Diagnosis in RANs

2026-06-01

AI Summary

This work addresses the challenge of efficiently diagnosing degraded Quality of Experience (QoE) in wireless Radio Access Networks (RANs) by proposing an end-to-end, large language model (LLM)-driven agent system. The system integrates a stateful central planner that orchestrates anomaly detection, causal tracing, and root cause localization modules, synergistically combining LLM-based reasoning, deterministic time-series KPI analysis tools, protocol-constraint knowledge bases, and historical expert cases to form an interpretable, closed-loop automated diagnostic framework. Evaluated on real-world RAN datasets, the system improves diagnostic accuracy by 18%–40% over strong baselines, reduces per-case diagnosis time from 30 minutes to 3 minutes, and generates expert-level interpretable reports—all while maintaining compatibility with multiple LLMs.

Abstract

Diagnosing Quality-of-Experience (QoE) degradations in operational Radio Access Networks (RANs) is a critical but notoriously complex task, traditionally requiring labor-intensive expert analysis over high-dimensional, cross-layer telemetry. While Large Language Models (LLMs) offer unprecedented reasoning capabilities, they are fundamentally unsuited for raw RANs troubleshooting: they fail at numeric time-series analysis, hallucinate protocol-violating causal links, and lack the stateful rigor required for multi-step fault localization. To bridge this gap, we present QoEReasoner, an end-to-end, LLM-driven agentic system designed for automated and explainable QoE diagnosis. QoEReasoner tames the inherent unpredictability of LLMs by grounding their reasoning in the physical realities of the network. It employs deterministic tools to reliably translate raw numeric KPIs into structured evidence, enforces protocol-consistent fault propagation through a domain-specific Knowledge Base, and leverages a Historical Bank of expert-validated cases to guide hypothesis generation. A stateful central planner orchestrates this closed-loop process across anomaly detection, causal tracing, and root-cause localization. Evaluations on real-world operational RANs datasets demonstrate that QoEReasoner outperforms strong baselines by 18\%-40\% in accuracy across multiple diagnostic tasks. Furthermore, it reduces diagnostic time from approximately 30 minutes of manual expert analysis to just 3 minutes per session, delivering highly interpretable, expert-grade reports while remaining robust across diverse LLM backbones.

Problem

• Quality-of-Experience
• Radio Access Networks
• QoE diagnosis
• network troubleshooting
• fault localization

Innovation

• Agentic Reasoning
• QoE Diagnosis
• LLM Grounding
• Protocol-Consistent Causality
• Automated Root-Cause Localization