Leveraging Large Language Models for Real-Time Agent Assist in Contact Centers: A Framework for Reducing Average Handle Time and Improving Customer Satisfaction

Read full text Summarise with VIRAT
Authors: Balakrishnan Devaraj
Cited by: 0
References: 9

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Contact centers are central nodes in enterprise customer engagement, yet they persistently contend with high operational costs and inconsistent service quality. The emergence of large language models (LLMs) presents a transformative opportunity through real-time agent assist capabilities. This paper proposes a deployment framework integrating LLMs via retrieval-augmented generation (RAG) architectures into live contact center workflows to provide agents with contextual suggestions and dynamic knowledge retrieval. Drawing on deployment observations and comparative analysis across representative enterprise environments, this study demonstrates that LLM-based agent assist systems can reduce average handle time (AHT) by 18 to 27 percent and produce measurable improvements in customer satisfaction scores. The paper discusses architectural considerations, integration challenges, ethical safeguards, and a phased adoption roadmap for practitioners.

Fields of Study & Subjects

AI in Service Interactions Artificial Intelligence Applications Customer Service Quality and Loyalty

Publication details

Journal / source
European Journal of Computer Science and Information Technology
Volume
14
Issue
2
Pages
67–73
Publication date
1 January 2026
Language
EN