@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://preview.aclanthology.org/ingest-acl/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 $0.41 per participant. These results suggest that by shifting from self-report inventory to behavior-grounded dialogue, MASA offers a more accurate, cost-effective, and transparent solution for real-world cognitive evaluation.$"
}