Date
Publisher
arXiv
This study introduces the AI-Educational Development Loop (AI-EDL), a theory-driven framework that integrates classical learning theories with human-in-the-loop artificial intelligence (AI) to support reflective, iterative learning. Implemented in EduAlly, an AI-assisted platform for writing-intensive and feedback-sensitive tasks, the framework emphasizes transparency, self-regulated learning, and pedagogical oversight. A mixed-methods study was piloted at a comprehensive public university to evaluate alignment between AI-generated feedback, instructor evaluations, and student self-assessments; the impact of iterative revision on performance; and student perceptions of AI feedback. Quantitative results demonstrated statistically significant improvement between first and second attempts, with agreement between student self-evaluations and final instructor grades. Qualitative findings indicated students valued immediacy, specificity, and opportunities for growth that AI feedback provided. These findings validate the potential to enhance student learning outcomes through developmentally grounded, ethically aligned, and scalable AI feedback systems. The study concludes with implications for future interdisciplinary applications and refinement of AI-supported educational technologies.
Study at a glance
- Question: How does an AI-assisted iterative feedback system affect student revision performance and align with teacher and student evaluations?
- Setting and data: Mid-size public university in northeastern United States; undergraduate and graduate special education students; 962 teacher-graded initial submissions, 963 resubmissions, and 74 student self-evaluations.
- Method: Mixed methods combining Wilcoxon signed-rank tests, Spearman rank correlations, and qualitative open coding of student reflections.
Why it matters
Most educational AI tools prioritize automation and efficiency while overlooking foundational learning theories. When tools function as black boxes and marginalize instructors, they fail to support reflective practice and co-constructed learning.
Key findings
- Student performance improved significantly between initial attempts and resubmissions after receiving AI feedback, with teacher grades rising from 1.56 to 1.77 on average.
- Teacher-assigned grades on first attempts were significantly higher than AI grades, with AI adhering rigidly to answer keys while teachers showed flexibility.
- Student self-evaluations showed no statistically significant difference from the instructor's final holistic grades, indicating close agreement between self-assessments and teacher evaluations.
Summary drafted with AI from the full paper and may contain errors. See the full paper for details.
What is the application?
Who age?
Why use AI?
Study design
