Emotionally Intelligent Task-oriented Dialogue Systems: Architecture, Representation, and Optimisation

TL;DR

This paper presents LUSTER, an LLM-based unified system for task-oriented dialogue that integrates emotional understanding and reinforcement learning to improve resilience and responsiveness in noisy conversational environments.

Contribution

It introduces LUSTER, a novel end-to-end reinforcement learning framework combining structured rewards and LLMs for emotionally intelligent task-oriented dialogue systems.

Findings

LUSTER improves task success rates in noisy environments.

Emotionally responsive systems enhance user satisfaction.

Structured reward modeling increases system resilience.

Abstract

Task-oriented dialogue (ToD) systems are designed to help users achieve specific goals through natural language interaction. While recent advances in large language models (LLMs) have significantly improved linguistic fluency and contextual understanding, building effective and emotionally intelligent ToD systems remains a complex challenge. Effective ToD systems must optimise for task success, emotional understanding and responsiveness, and precise information conveyance, all within inherently noisy and ambiguous conversational environments. In this work, we investigate architectural, representational, optimisational as well as emotional considerations of ToD systems. We set up systems covering these design considerations with a challenging evaluation environment composed of a natural-language user simulator coupled with an imperfect natural language understanding module. We propose \textbf{LUSTER}, an \textbf{L}LM-based \textbf{U}nified \textbf{S}ystem for \textbf{T}ask-oriented dialogue with \textbf{E}nd-to-end \textbf{R}einforcement learning with both short-term (user sentiment) and long-term (task success) rewards. Our findings demonstrate that combining LLM capability with structured reward modelling leads to more resilient and emotionally responsive ToD systems, offering a practical path forward for next-generation conversational agents.