@inproceedings{li-etal-2026-decision,
title = "Decision-aware User Simulation Agent for Evaluating Conversational Recommender Systems",
author = "Li, Yuan-Chi and
Chen, Li-Chi and
Wu, Sung-Yi and
Tsai, Yu-Che and
Lin, Shou-De",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.77/",
pages = "1572--1592",
ISBN = "979-8-89176-462-0",
abstract = "Conversational recommender systems (CRS) increasingly rely on user simulators for automated evaluation of sales agents. A key requirement for such simulators is the ability to model human decision-making. However, most LLM-based simulators often exhibit unrealistically strong information-processing capabilities, rarely exhibiting the hesitation and decision deferral commonly observed in real consumer behavior, resulting in overly high acceptance rates. To address this limitation, we propose Hesitator, a theory-grounded user simulation framework that explicitly models a specific dimension of human decision-making: decision deferral under choice overload. The framework introduces a modular Decision Module that separates utility-based item selection from overload-aware commitment decisions. Experiments across multiple user simulation frameworks, domains, sales modes, and LLM backbones show that integrating our module consistently mitigates unrealistic behaviors under increasing overload conditions. Furthermore, Hesitator reproduces established findings from behavioral economics, demonstrating its ability to model human decision behavior."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-decision">
<titleInfo>
<title>Decision-aware User Simulation Agent for Evaluating Conversational Recommender Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuan-Chi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li-Chi</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sung-Yi</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu-Che</namePart>
<namePart type="family">Tsai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shou-De</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Conversational recommender systems (CRS) increasingly rely on user simulators for automated evaluation of sales agents. A key requirement for such simulators is the ability to model human decision-making. However, most LLM-based simulators often exhibit unrealistically strong information-processing capabilities, rarely exhibiting the hesitation and decision deferral commonly observed in real consumer behavior, resulting in overly high acceptance rates. To address this limitation, we propose Hesitator, a theory-grounded user simulation framework that explicitly models a specific dimension of human decision-making: decision deferral under choice overload. The framework introduces a modular Decision Module that separates utility-based item selection from overload-aware commitment decisions. Experiments across multiple user simulation frameworks, domains, sales modes, and LLM backbones show that integrating our module consistently mitigates unrealistic behaviors under increasing overload conditions. Furthermore, Hesitator reproduces established findings from behavioral economics, demonstrating its ability to model human decision behavior.</abstract>
<identifier type="citekey">li-etal-2026-decision</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.77/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>1572</start>
<end>1592</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Decision-aware User Simulation Agent for Evaluating Conversational Recommender Systems
%A Li, Yuan-Chi
%A Chen, Li-Chi
%A Wu, Sung-Yi
%A Tsai, Yu-Che
%A Lin, Shou-De
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F li-etal-2026-decision
%X Conversational recommender systems (CRS) increasingly rely on user simulators for automated evaluation of sales agents. A key requirement for such simulators is the ability to model human decision-making. However, most LLM-based simulators often exhibit unrealistically strong information-processing capabilities, rarely exhibiting the hesitation and decision deferral commonly observed in real consumer behavior, resulting in overly high acceptance rates. To address this limitation, we propose Hesitator, a theory-grounded user simulation framework that explicitly models a specific dimension of human decision-making: decision deferral under choice overload. The framework introduces a modular Decision Module that separates utility-based item selection from overload-aware commitment decisions. Experiments across multiple user simulation frameworks, domains, sales modes, and LLM backbones show that integrating our module consistently mitigates unrealistic behaviors under increasing overload conditions. Furthermore, Hesitator reproduces established findings from behavioral economics, demonstrating its ability to model human decision behavior.
%U https://aclanthology.org/2026.findings-emnlp.77/
%P 1572-1592
Markdown (Informal)
[Decision-aware User Simulation Agent for Evaluating Conversational Recommender Systems](https://aclanthology.org/2026.findings-emnlp.77/) (Li et al., Findings 2026)
ACL