@inproceedings{lu-etal-2026-breaking,
title = "Breaking the Script: Do Role-Playing Agents Maintain Goal Alignment under Distraction?",
author = "Lu, Dongxu and
Gatt, Albert and
Jeuring, Johan",
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-1.8/",
pages = "107--123",
abstract = "As large language models (LLMs) are increasingly deployed as role-playing agents in educational and professional training simulations, their susceptibility to user-induced distraction threatens their pedagogical utility. We formalise goal-competing distraction as a controlled evaluation paradigm and introduce a simulation framework that captures both immediate reactions and multi-turn trajectories under targeted distraction, using an LLM-based user simulator. Building upon this framework, we evaluate agent behaviour across three models: Gemini-2.0-Flash, Llama-3.3-70B-Instruct, and Llama-3.1-8B-Instruct. Our findings reveal a critical trade-off dependent on model scale. While larger models tend to remain socially responsive and more frequently engage with distractor topics, the smaller model shows rigid goal adherence by resisting and rejecting distraction. Although redirection is the most common initial response, subsequent trajectories diverge substantially. The inclusion of explicit dialogue state demonstrates model-dependent effects, acting as a stabilising anchor for smaller models but providing limited benefit for larger ones. These results suggest that maintaining goal alignment in role-playing agents requires explicitly managing the trade-off between conversational responsiveness and goal adherence."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lu-etal-2026-breaking">
<titleInfo>
<title>Breaking the Script: Do Role-Playing Agents Maintain Goal Alignment under Distraction?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dongxu</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Albert</namePart>
<namePart type="family">Gatt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johan</namePart>
<namePart type="family">Jeuring</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>As large language models (LLMs) are increasingly deployed as role-playing agents in educational and professional training simulations, their susceptibility to user-induced distraction threatens their pedagogical utility. We formalise goal-competing distraction as a controlled evaluation paradigm and introduce a simulation framework that captures both immediate reactions and multi-turn trajectories under targeted distraction, using an LLM-based user simulator. Building upon this framework, we evaluate agent behaviour across three models: Gemini-2.0-Flash, Llama-3.3-70B-Instruct, and Llama-3.1-8B-Instruct. Our findings reveal a critical trade-off dependent on model scale. While larger models tend to remain socially responsive and more frequently engage with distractor topics, the smaller model shows rigid goal adherence by resisting and rejecting distraction. Although redirection is the most common initial response, subsequent trajectories diverge substantially. The inclusion of explicit dialogue state demonstrates model-dependent effects, acting as a stabilising anchor for smaller models but providing limited benefit for larger ones. These results suggest that maintaining goal alignment in role-playing agents requires explicitly managing the trade-off between conversational responsiveness and goal adherence.</abstract>
<identifier type="citekey">lu-etal-2026-breaking</identifier>
<location>
<url>https://aclanthology.org/2026.sigdial-1.8/</url>
</location>
<part>
<date>2026-08</date>
<extent unit="page">
<start>107</start>
<end>123</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Breaking the Script: Do Role-Playing Agents Maintain Goal Alignment under Distraction?
%A Lu, Dongxu
%A Gatt, Albert
%A Jeuring, Johan
%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 lu-etal-2026-breaking
%X As large language models (LLMs) are increasingly deployed as role-playing agents in educational and professional training simulations, their susceptibility to user-induced distraction threatens their pedagogical utility. We formalise goal-competing distraction as a controlled evaluation paradigm and introduce a simulation framework that captures both immediate reactions and multi-turn trajectories under targeted distraction, using an LLM-based user simulator. Building upon this framework, we evaluate agent behaviour across three models: Gemini-2.0-Flash, Llama-3.3-70B-Instruct, and Llama-3.1-8B-Instruct. Our findings reveal a critical trade-off dependent on model scale. While larger models tend to remain socially responsive and more frequently engage with distractor topics, the smaller model shows rigid goal adherence by resisting and rejecting distraction. Although redirection is the most common initial response, subsequent trajectories diverge substantially. The inclusion of explicit dialogue state demonstrates model-dependent effects, acting as a stabilising anchor for smaller models but providing limited benefit for larger ones. These results suggest that maintaining goal alignment in role-playing agents requires explicitly managing the trade-off between conversational responsiveness and goal adherence.
%U https://aclanthology.org/2026.sigdial-1.8/
%P 107-123
Markdown (Informal)
[Breaking the Script: Do Role-Playing Agents Maintain Goal Alignment under Distraction?](https://aclanthology.org/2026.sigdial-1.8/) (Lu et al., SIGDIAL 2026)
ACL