@inproceedings{li-etal-2026-beyond-self,
title = "Beyond Self-Report: Bridging the Intention-Behavior Gap in Critical Thinking Assessment via Interpretable Multi-Agent System",
author = "Li, Zekun and
Yu, Jifan and
Li, Haoxuan and
He, Ye and
Zhang-Li, Daniel and
Tu, Shangqing and
Lim, Joy Jia Yin and
Jiang, Yikun and
Yuan, Jiaxin and
Zhang, Yu",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1236/",
pages = "26849--26871",
ISBN = "979-8-89176-390-6",
abstract = "Accurate assessment of critical thinking is historically limited by the Intention Behavior Gap in psychology: the disconnect between what individuals self-reported disposition and their actual practical behaviors. We try to bridge this gap with MASA (Multi-Agent Scenario-based Assessment), a framework that operationalizes cognitive assessment into an interpretable and interactive multi-agent workflow with Assessment Chain-of-Thought (AsCoT). Validating on both large-scale simulations (N=1,161) and human participants (N=70), we find that MASA aligns better with human expert ratings (r=0.882) than traditional gold-standard inventories (r=0.720), with an average cost of only $0.41 per participant. These results suggest that by shifting from self-report inventory to behavior-grounded dialogue, MASA offers a more accurate, cost-effective, and transparent solution for real-world cognitive evaluation.$"
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2026-beyond-self">
<titleInfo>
<title>Beyond Self-Report: Bridging the Intention-Behavior Gap in Critical Thinking Assessment via Interpretable Multi-Agent System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zekun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jifan</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haoxuan</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ye</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Zhang-Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shangqing</namePart>
<namePart type="family">Tu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joy</namePart>
<namePart type="given">Jia</namePart>
<namePart type="given">Yin</namePart>
<namePart type="family">Lim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yikun</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxin</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Accurate assessment of critical thinking is historically limited by the Intention Behavior Gap in psychology: the disconnect between what individuals self-reported disposition and their actual practical behaviors. We try to bridge this gap with MASA (Multi-Agent Scenario-based Assessment), a framework that operationalizes cognitive assessment into an interpretable and interactive multi-agent workflow with Assessment Chain-of-Thought (AsCoT). Validating on both large-scale simulations (N=1,161) and human participants (N=70), we find that MASA aligns better with human expert ratings (r=0.882) than traditional gold-standard inventories (r=0.720), with an average cost of only 0.41 per participant. These results suggest that by shifting from self-report inventory to behavior-grounded dialogue, MASA offers a more accurate, cost-effective, and transparent solution for real-world cognitive evaluation.</abstract>
<identifier type="citekey">li-etal-2026-beyond-self</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1236/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>26849</start>
<end>26871</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Beyond Self-Report: Bridging the Intention-Behavior Gap in Critical Thinking Assessment via Interpretable Multi-Agent System
%A Li, Zekun
%A Yu, Jifan
%A Li, Haoxuan
%A He, Ye
%A Zhang-Li, Daniel
%A Tu, Shangqing
%A Lim, Joy Jia Yin
%A Jiang, Yikun
%A Yuan, Jiaxin
%A Zhang, Yu
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F li-etal-2026-beyond-self
%X Accurate assessment of critical thinking is historically limited by the Intention Behavior Gap in psychology: the disconnect between what individuals self-reported disposition and their actual practical behaviors. We try to bridge this gap with MASA (Multi-Agent Scenario-based Assessment), a framework that operationalizes cognitive assessment into an interpretable and interactive multi-agent workflow with Assessment Chain-of-Thought (AsCoT). Validating on both large-scale simulations (N=1,161) and human participants (N=70), we find that MASA aligns better with human expert ratings (r=0.882) than traditional gold-standard inventories (r=0.720), with an average cost of only 0.41 per participant. These results suggest that by shifting from self-report inventory to behavior-grounded dialogue, MASA offers a more accurate, cost-effective, and transparent solution for real-world cognitive evaluation.
%U https://aclanthology.org/2026.acl-long.1236/
%P 26849-26871
Markdown (Informal)
[Beyond Self-Report: Bridging the Intention-Behavior Gap in Critical Thinking Assessment via Interpretable Multi-Agent System](https://aclanthology.org/2026.acl-long.1236/) (Li et al., ACL 2026)
ACL
- Zekun Li, Jifan Yu, Haoxuan Li, Ye He, Daniel Zhang-Li, Shangqing Tu, Joy Jia Yin Lim, Yikun Jiang, Jiaxin Yuan, and Yu Zhang. 2026. Beyond Self-Report: Bridging the Intention-Behavior Gap in Critical Thinking Assessment via Interpretable Multi-Agent System. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 26849–26871, San Diego, California, United States. Association for Computational Linguistics.