Studies of AITutor with 12 students reveal that layered worked examples, visual grounding, and metacognitive scaffolding reduce the cost of reasoning repair while students repurpose shortcuts as checkpoints under exam pressure.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.HC 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
From Answer Generators to Reasoning Facilitators: Designing AI Tutors for Mathematical Reasoning in High-Stakes Environments
Studies of AITutor with 12 students reveal that layered worked examples, visual grounding, and metacognitive scaffolding reduce the cost of reasoning repair while students repurpose shortcuts as checkpoints under exam pressure.