Personalized problem selection enhances student practice in tutoring systems. Prior research has focused on transparent problem selection that supports learner control but rarely engages learners in selecting practice materials. We explored how different levels of control (i.e., full AI control, shared control, and full learner control), combined…

Learners' choices as to whether and how to use visual representations during learning are an important yet understudied aspect of self-regulated learning. To gain insight, we developed a "choice-based" intelligent tutor in which students can choose whether and when to use diagrams to aid their problem solving in algebra. In an…