Learning to Prompt: Improving Student Engagement with Adaptive LLM-based High-School Tutoring
arXiv:2606.20138v1 Announce Type: cross Abstract: LLMs can personalize education, although current static-prompt tutoring systems struggle to adapt to diverse academic disciplines. We develop and test a system with subject-aware prompting, based on 14 pedagogical features (e.g., tutor scaffolding, student understanding) extracted from raw transcripts. We first train a prompt routing model in a simulation environment, and then deploy it for online adaptation with actual high-school students. The simulation benchmark shows the router outperforming two static baselines ($0.694$ vs. $0.647$ and $0
The rapid advancement and widespread adoption of LLMs are enabling new applications in personalized education, moving beyond static systems to more adaptive approaches.
This development indicates a tangible step towards more effective and personalized AI-driven education, potentially enhancing student outcomes and challenging traditional pedagogical models.
LLM-based tutoring systems are evolving from static prompts to dynamic, adaptive interactions based on sophisticated pedagogical features, improving their efficacy across diverse academic subjects.
- · AI education providers
- · Students
- · EdTech companies
- · LLM developers
- · Traditional tutoring services
- · Static e-learning platforms
- · Educators resistant to AI integration
The adoption of subject-aware prompting will lead to more engaging and effective AI tutors that adapt to individual student needs.
Improved student engagement and learning outcomes could lead to a re-evaluation of high-school curricula and teaching methodologies to better integrate AI-powered tools.
Successful deployment of adaptive LLM tutors could reduce educational inequities by providing high-quality, personalized instruction to a broader student population, potentially impacting academic achievement disparities.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.CL