Boosting Student Engagement in STEM: Integrating Large Language Model‐Based Virtual Agents Into Alternate Reality Games.

Background: STEM education aims to develop innovation and problem‐solving skills through interdisciplinary learning, yet struggles to foster student engagement and interdisciplinary thinking. Whilst alternate reality games (ARGs) can boost motivation via game‐based problem‐solving, integrating large...

Descripción completa

Detalles Bibliográficos
Publicado en:Journal of Computer Assisted Learning Vol. 41; no. 6; pp. 1 - 20
Autores principales: Wang, Minkai, Zhu, Jingdong, Hwang, Gwo‐Jen, Chang, Shao‐Chen, Yang, Qi‐Fan, Zhang, Di
Formato: clinical trial pictorial research tables/charts Journal Article
Publicado: Wiley-Blackwell Dec2025
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ccm&AN=189524199&site=ehost-live
header:
  @attributes:
    shortDbName: ccm
    uiTerm: 189524199
    longDbName: CINAHL Complete
    uiTag: AN
  controlInfo:
    bkinfo:
    dissinfo:
    jinfo:
      jid:
        02664909
        6M1
      jtl: Journal of Computer Assisted Learning
      issn: 02664909
      maglogo: Y
    pubinfo:
      dt: Dec2025
      vid: 41
      iid: 6
      pid: 480
      pub: Wiley-Blackwell
      place: Malden, Massachusetts
    artinfo:
      ui:
        189524199
        189524199
        189524199
        10.1111/jcal.70139
        189524199
      ppf: 1
      ppct: 19
      formats:
      tig:
        atl: Boosting Student Engagement in STEM: Integrating Large Language Model‐Based Virtual Agents Into Alternate Reality Games.
      aug:
        au:
          Wang, Minkai
          Zhu, Jingdong
          Hwang, Gwo‐Jen
          Chang, Shao‐Chen
          Yang, Qi‐Fan
          Zhang, Di
        affil: College of Education, Zhejiang University of Technology, Hangzhou, China
      sug:
        subj:
          Science Education
          Technology Education
          Engineering Education
          Mathematics Education
          Students, Elementary Psychosocial Factors
          Artificial Intelligence, Generative
          Learning Methods
          Video Games
          Student Attitudes Evaluation
          Motivation Evaluation
          Academic Performance Evaluation
          Cognition Evaluation
          Learning Evaluation
          Computer-Assisted Instruction
          Program Evaluation
          Human
          Child
          Adolescence
          China
          Schools, Elementary
          Quasi-Experimental Studies
          Male
          Female
          Problem Solving
          Education, Interdisciplinary
          Feedback
          Pretest-Posttest Control Group Design
          Clinical Trials
          Funding Source
          Questionnaires
          Analysis of Covariance
          Pearson's Correlation Coefficient
          Correlational Studies
          Comparative Studies
          Systems Design
          Software Design
          Summated Rating Scaling
          Quantitative Studies
          Descriptive Statistics
          Task Performance and Analysis
          Child Behavior Evaluation
          Adolescent Behavior Evaluation
          Exploratory Research
          Regression
          Child: 6-12 years
          Adolescent: 13-18 years
          Male
          Female
      ab: Background: STEM education aims to develop innovation and problem‐solving skills through interdisciplinary learning, yet struggles to foster student engagement and interdisciplinary thinking. Whilst alternate reality games (ARGs) can boost motivation via game‐based problem‐solving, integrating large language models (LLMs) remains underexplored. LLM‐based virtual agents offer new opportunities for adaptive support. Objectives: This study aimed to investigate the effectiveness of an LLM‐assisted ARG system (LLM‐ARG) in enhancing academic performance, metacognitive awareness, and engagement. Methods: A quasi‐experimental study compared LLM‐ARG with conventional ARG methods amongst primary school students. The experimental group used LLM‐ARG with personalised virtual agent support, whilst the control group employed a conventional ARG with a traditional, rule‐based virtual agent that offered only pre‐scripted feedback. Data were collected through pre‐ and post‐tests, metacognitive awareness questionnaires, and interaction logs. ANCOVA and correlation analyses were conducted. Results and Conclusions: LLM‐ARG significantly improved learning achievements and metacognitive awareness compared to conventional ARG. High‐frequency interactions promoted exploration but did not consistently enhance problem‐solving, whilst low‐frequency interactions led to higher success via goal‐directed strategies. Metacognitive competence emerged as a key predictor of academic performance, highlighting the need to balance exploration with efficiency. This study demonstrates how LLM‐driven scaffolding supports diverse learning strategies and promotes adaptive learning in STEM education.
      pubtype: Academic Journal
      doctype:
        clinical trial
        pictorial
        research
        tables/charts
        Journal Article
      ougenre: Article
    language: English
    refInfo:
    holdings:
      @attributes:
        islocal: N