Multi-Agent LLM System for End-to-End Voice of Customer (VOC) Analysis

Abstract

Voice of the Customer (VOC) programs are critical in shaping customer experience management, yet traditional methods are slow, siloed, and limited in depth. While large language models (LLMs) offer promise in synthesizing customer feedback, single-agent systems fall short in delivering actionable insights. This research proposes a multi-agent LLM framework that structures VOC analysis into specialized layers: synthesis, trend detection, root cause analysis, recommendation, and monitoring. A proof-of-concept using anonymized VOC data demonstrates the potential of this framework to improve scalability, accountability, and root-cause driven insights at a significantly lower operationalization cost. Contributions include (1) an architecture tailored for end-to-end VOC workflows, and (2) demonstration of its application in enterprise contexts.

Keywords — Voice of Customer (VOC), LLM, Multi-agent , Root Cause Analysis, Customer Insights