Microsoft's StudentSim uses error-prone simulated students to train better AI tutors

The Decoder · rss · 2026-09-20

Microsoft and the University of Illinois built StudentSim, which recreates individual students from limited data and makes them make realistic mistakes, giving AI tutors fast, low-cost feedback. Across tests with 60 students in chess, English, and math, tutors trained with StudentSim outperformed GPT-5.4, and a chess tutor trained this way earned the highest expert ratings among three versions tested.

Original post →

More from Research

Research channel →