AI/Paper/25/Effective Personalized AI Tutors via LLM-Guided Reinforcement Learning
Properties
- logseq-entity
- Logseq/Entity/Article
Effective Personalized AI Tutors via LLM-Guided Reinforcement Learning
- PDF preprint — Working Paper
Generative AI (GenAI) is rapidly reshaping education by unlocking the potential for personalized tutoring. Yet, emerging platforms largely focus on GenAI chatbot tutors that reactively answer student questions. We design a novel tutoring platform that tightly integrates a carefully-designed GenAI chatbot with a reinforcement learning algorithm for sequencing practice problems. This algorithm leverages rich signals from student-chatbot interactions to adaptively select practice problems of an appropriate difficulty level.
Key Findings
- Randomized controlled trial across 10 high schools in Taipei (n=770 students) — 5-month "AI for Python Learning" course with Taipei City Government and American Institute in Taiwan
- Adaptive problem sequencing (RL-guided) vs fixed sequence
- Adaptive sequencing increased unassisted final exam performance by 0.15 standard deviations (≈ 6–9 months of schooling)
- Mediation analysis: gains driven by increased engagement
- LLMs used both to measure quality of student-chatbot conversations and to analyze student solution attempts, enabling richer knowledge-state estimation than binary correct/incorrect signals
Authors
Links