EUVIMEDOpdag EUVIMED
Mixed-Methods-StudieOpen access · CC BY 4.0

The Effects of Agent Type and Feedback Style on Self-Directed Learning: A Mixed-Methods Study

Xue Han iD, Jing Cao, Zi Wang, Heng Luo iD

Behavioral Sciences · 2026-06-30 · 16 (7) · 1069

DOI: 10.3390/bs16071069 ↗

At a glance

Mixed-Methods-Studie in Behavioral Sciences, published online on 2026-06-30. Written by Xue Han and 3 co-authors. Institution: Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, China. 108 references. The full text is freely available (open access, CC BY 4.0). Funded by: Central China Normal University.

AbstractSubjectsBibliografiske oplysningerCiteRelated studies

Abstract (original language)

This study examines how agent type (customized vs. general-purpose) and feedback style (Socratic vs. directive) are associated with learners’ engagement with artificial intelligence (AI)-generated feedback in self-directed learning (SDL), with particular attention to patterns in feedback quality, self-regulatory behaviors, learning experiences, and learning outcomes. A 2 × 2 mixed factorial experiment was conducted with 51 postgraduate students who completed two instructional design tasks under different feedback conditions. Quantitative results indicated that customized agents generated feedback with higher accuracy and specificity than general-purpose agents. Socratic feedback was associated with stronger comprehension monitoring, whereas directive feedback was associated with higher cognitive load. A significant interaction suggested that the advantage of customized agents in learning outcomes, operationalized as short-term task improvement, emerged under directive feedback but not under Socratic feedback. Qualitative analysis indicated that Socratic prompts encouraged deeper, logic-oriented reflection, whereas directive feedback provided actionable guidance that facilitated task completion. Learners adopted feedback selectively based on perceived accuracy, and trust in customized agents was higher when feedback was clear and contextually aligned. These findings suggest that the effectiveness of AI-generated feedback is shaped not only by agent type and feedback style but also by how learners evaluate and use feedback.

Subjects

Author keywords

agent typeartificial intelligencefeedback stylehuman–AI interactionmixed methodsself-directed learningself-regulation

Authors and institutions

  • Faculty of Artificial Intelligence in Education, Central China Normal University, Wuhan 430079, China.

ORCID profiles: Xue Han, Heng Luo

Funding

  • Central China Normal University

Cite

APA

Han, X., Cao, J., Wang, Z., & Luo, H. (2026). The Effects of Agent Type and Feedback Style on Self-Directed Learning: A Mixed-Methods Study. Behavioral Sciences, 16(7), 1069. https://doi.org/10.3390/bs16071069

Vancouver

Han X, Cao J, Wang Z, Luo H. The Effects of Agent Type and Feedback Style on Self-Directed Learning: A Mixed-Methods Study. Behavioral Sciences. 2026;16(7):1069. doi:10.3390/bs16071069

BibTeX
@article{Han2026,
  author = {Han, Xue and Cao, Jing and Wang, Zi and Luo, Heng},
  title = {The Effects of Agent Type and Feedback Style on Self-Directed Learning: A Mixed-Methods Study},
  journal = {Behavioral Sciences},
  year = {2026},
  volume = {16},
  number = {7},
  pages = {1069},
  doi = {10.3390/bs16071069}
}
Start for free →