@inproceedings{abulimiti-etal-2026-reinforcement,
title = "A Reinforcement Learning-Based Facilitator for Simulated Group Motivational Interviewing",
author = "Abulimiti, Alafate and
Maraev, Vladislav and
Helme-Guizon, Agn{\`e}s and
Pelachaud, Catherine",
editor = "Choi, Jinho D. and
Chen, Yun-Nung and
Funakoshi, Kotaro and
Emami, Ali",
booktitle = "Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue",
month = aug,
year = "2026",
address = "Atlanta, Georgia, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.sigdial-1.61/",
pages = "871--890",
abstract = "Motivational Interviewing (MI) is a widely validated approach to behavior change, but existing virtual MI agents operate only in one-on-one settings, ignoring the cost-effectiveness and peer-support dynamics of group MI. We present a simulation environment and reinforcement learning (RL) based dialogue manager for group MI, in which a discrete Soft-Actor-Critic (SAC) policy selects therapist dialogue acts and a large language model generates utterances, with two LLM-prompted patient agents as interlocutors. Our model supports adaptation to different participant profiles. We compared our dialogue manager with four LLM-based ones at the dialogue acts level. We observed that RL yields a significantly different therapist policy, which showed the tendency to generate more directive acts and adapt to varying group compositions. Participant profile adaptation was the strongest in groups containing an open-to-change participant."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abulimiti-etal-2026-reinforcement">
<titleInfo>
<title>A Reinforcement Learning-Based Facilitator for Simulated Group Motivational Interviewing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alafate</namePart>
<namePart type="family">Abulimiti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vladislav</namePart>
<namePart type="family">Maraev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agnès</namePart>
<namePart type="family">Helme-Guizon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catherine</namePart>
<namePart type="family">Pelachaud</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinho</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Choi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kotaro</namePart>
<namePart type="family">Funakoshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ali</namePart>
<namePart type="family">Emami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Atlanta, Georgia, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Motivational Interviewing (MI) is a widely validated approach to behavior change, but existing virtual MI agents operate only in one-on-one settings, ignoring the cost-effectiveness and peer-support dynamics of group MI. We present a simulation environment and reinforcement learning (RL) based dialogue manager for group MI, in which a discrete Soft-Actor-Critic (SAC) policy selects therapist dialogue acts and a large language model generates utterances, with two LLM-prompted patient agents as interlocutors. Our model supports adaptation to different participant profiles. We compared our dialogue manager with four LLM-based ones at the dialogue acts level. We observed that RL yields a significantly different therapist policy, which showed the tendency to generate more directive acts and adapt to varying group compositions. Participant profile adaptation was the strongest in groups containing an open-to-change participant.</abstract>
<identifier type="citekey">abulimiti-etal-2026-reinforcement</identifier>
<location>
<url>https://aclanthology.org/2026.sigdial-1.61/</url>
</location>
<part>
<date>2026-08</date>
<extent unit="page">
<start>871</start>
<end>890</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Reinforcement Learning-Based Facilitator for Simulated Group Motivational Interviewing
%A Abulimiti, Alafate
%A Maraev, Vladislav
%A Helme-Guizon, Agnès
%A Pelachaud, Catherine
%Y Choi, Jinho D.
%Y Chen, Yun-Nung
%Y Funakoshi, Kotaro
%Y Emami, Ali
%S Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue
%D 2026
%8 August
%I Association for Computational Linguistics
%C Atlanta, Georgia, USA
%F abulimiti-etal-2026-reinforcement
%X Motivational Interviewing (MI) is a widely validated approach to behavior change, but existing virtual MI agents operate only in one-on-one settings, ignoring the cost-effectiveness and peer-support dynamics of group MI. We present a simulation environment and reinforcement learning (RL) based dialogue manager for group MI, in which a discrete Soft-Actor-Critic (SAC) policy selects therapist dialogue acts and a large language model generates utterances, with two LLM-prompted patient agents as interlocutors. Our model supports adaptation to different participant profiles. We compared our dialogue manager with four LLM-based ones at the dialogue acts level. We observed that RL yields a significantly different therapist policy, which showed the tendency to generate more directive acts and adapt to varying group compositions. Participant profile adaptation was the strongest in groups containing an open-to-change participant.
%U https://aclanthology.org/2026.sigdial-1.61/
%P 871-890
Markdown (Informal)
[A Reinforcement Learning-Based Facilitator for Simulated Group Motivational Interviewing](https://aclanthology.org/2026.sigdial-1.61/) (Abulimiti et al., SIGDIAL 2026)
ACL