StudentSim: Training LLM-based Student Simulators

Researchers introduced StudentSim, a method for training LLM-based student simulators that generate synthetic learning data to help AI tutors adapt to individual students, addressing the scarcity of real learner evidence. The approach aims to provide a faster, cheaper proxy for evaluating which guidance strategies work for which student profiles.

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 approach