ORIGINAL RESEARCH article
Front. Digit. Health
Sec. Human Factors and Digital Health
This article is part of the Research TopicDesigning for Engagement in Digital Health for Chronic and Long-Term CareView all 17 articles
Adapting Virtual Agent Interaction Style with Reinforcement Learning to Enhance Affective Engagement
Provisionally accepted
Christian Tamantini*
Alessandro Umbrico*
Francesca Fracasso
Gloria BeraldoGabriella Cortellessa
Andrea Orlandini- National Research Council (CNR), Roma, Italy
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
Introduction: The ability of artificial agents to dynamically adapt their communication style is a key factor in sustaining engagement during human-agent interaction. This study introduces a reinforcement learning-based framework for real-time modulation of interaction style, aiming to maximize the affective valence of the user's emotional response. The approach is domain-independent and designed for integration into scenarios where personalized and engaging dialogue is critical, such as in Behavior Change Interventions. Methods: To validate the system, we conducted a between-subjects user study involving N = 20 participants, who completed a structured task, i.e. the URICA questionnaire, delivered either by an adaptive speech-based agent or a static screen-based interface. In the adaptive condition, the virtual agent employed Thompson Sampling to select between two communication styles (enthusiastic and neutral) based on real-time facial emotion recognition. The goal of the system was to reinforce the style that increased or maintained valence across successive interaction turns. Results: The reinforcement learning system successfully adapted its behavior based on individual users' emotional feedback. Notably, a significant positive correlation was observed between users' Psychoticism scores and the reinforcement of the neutral style (Spearman's ρ = 0.70, p-value = 0.04), indicating sensitivity to personality traits. Although no significant differences emerged in user-reported experience between conditions, this highlights that the adaptive speech-based agent preserved usability while successfully personalizing interaction based on affective cues. Discussion: These findings highlight the potential of adaptive agents to personalize interaction strategies in emotionally relevant contexts, even when the subjective user experience appears similar to that of static systems. The ability to align communicative behavior with user personality profiles supports the feasibility of deploying such models in long-term interventions, where maintaining user motivation and engagement is essential.
Keywords: Adaptive Human-Agent Interaction, affective engagement, behavior change intervention, FaceEmotion Recognition, reinforcement learning
Received: 06 Aug 2025; Accepted: 03 Dec 2025.
Copyright: © 2025 Tamantini, Umbrico, Fracasso, Beraldo, Cortellessa and Orlandini. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence:
Christian Tamantini
Alessandro Umbrico
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.