Learning to Prompt: Improving Student Engagement with Adaptive LLM-based High-School Tutoring

Created: 2026-06-19 | Tags: intelligent-tutoringllmk-12personalized-learningscaffoldingadaptive-learning

Po-Chin Chang, Nicholas Hogan, Aske Plaat, Michiel T. van der Meer (2026). arXiv cs.AI preprint ๐Ÿ“„ Full text (arXiv)

Overview

Adaptive LLM tutoring with subject-aware prompt routing based on 14 pedagogical features. A/B test on 656 conversations from 359 Dutch high-school students showed sim-to-real transfer. A stochastic router achieved 28.1% exercise conversion rate vs 19.6% baseline. Reduces interaction turns by ~3 (p=0.007) while maintaining pedagogical quality.

Key Contributions

Paper 1: Code as Anchor, Memory and Metaphor as Support: Learner Experiences with Multi-View Visualizations

Paper 2: Learning to Prompt: Improving Student Engagement with Adaptive LLM-based High-School Tutoring

Paper 3: Confidence-Aware Automated Assessment of Student-Drawn Scientific Models

Paper 4: PsyScore: A Psychometrically-Aware Framework for Trait-Adaptive Essay Scoring and ZPD-Scaffolded Feedback

Related Pages

Citation

APA: Po-Chin Chang, Nicholas Hogan, Aske Plaat, Michiel T. van der Meer (2026). Learning to Prompt: Improving Student Engagement with Adaptive LLM-based High-School Tutoring. arXiv:2606.20138. arXiv cs.AI preprint.