StudentSim: Training LLM-based Student Simulators
Presents novel training methodology for creating individualized AI student proxies to improve adaptive tutoring systems.
AI Summary
Researchers introduce StudentSim, a framework for LLM-based student simulators that outperform GPT-5.4 in behavioral fidelity and guidance responsiveness across chess, language, and math domains.
Excerpt
AI tutors are most useful when they adapt to each student's strengths, weaknesses, and preferred guidance, but evidence about which guidance works for which student is sparse, slow, and costly to collect from real learners. Student simulators can provide this signal as a proxy, yet existing approaches are limited: state-tracking models fit student behavior but struggle to process explanations or corrections, while LLM role-play follows guidance fluently but does not reliably match the competence