StudentSim: Enhancing AI Tutoring Tools with Student Simulators

StudentSim is a research system designed to evaluate and enhance AI tutoring tools before they are tested with real learners. It trains personalized student simulators from publicly available, de-identified learner records, adapting one simulator for each student. StudentSim outperforms leading baselines across domains such as chess, second-language English writing, and mathematics, providing a valuable feedback signal for training AI tutors. Additionally, it introduces StudentSimEval, a benchmark and evaluation protocol that spans multiple educational areas.