After a failed scripted question, repeating it is followed by lower recovery than switching to addressing the student's error¶

Claim · All claims
Evidence · 1 study · associational r2 · q3
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? Repeating a scripted question after it failed was followed by recovery in 28.1% of cases (AOR = 0.48 vs onset), whereas switching to addressing the error preserved recovery at 39.8% (AOR = 0.78, not different from onset). → Ahtisham 2026

Evidence¶

Ahtisham 2026¶

Ahtisham, B., Vanacore, K., Napoli, A., Arens, J., Ionova, K., Cohn, C., Salehi, S., & Kizilcec, R. (2026). Examining Variation in How Guided AI Tutors Resolve Student Impasses. arXiv. https://arxiv.org/abs/2609.38346 doi:10.48550/arxiv.2609.38346

q3 · i? · associational · r2

Model 2 two-turn sequence analysis (Table 5) on impasse episodes, adjusted for depth, impasse type, and practice, relative to a first scripted question at onset (55.5% recovery). An order-free specification reproduced the pattern (30.5% vs 37.5%).

"When a scripted question followed another scripted question, recovery fell to 28.1%, halving the odds (AOR =0.48 , [0.34, 0.67], p< .001 ). Moving from a scripted question to addressing the student's error preserved recovery (39.8%; AOR=0.78 , p=.29 , not different from onset)."

Discussion¶

Related Claims¶

• Contingent scaffolding improves learning more than fixed or absent support. — the general claim this finding bears on, with the studies behind it
• Student impasses in LLM chemistry tutoring concentrate in the relevant-concepts planning phase, and impasse type depends strongly on problem-solving practice — related
• The association between tutor questioning and impasse recovery decays as impasses persist, while addressing the student's error becomes more beneficial — a broader claim this one bears on
• Next-turn recovery from impasses declines steadily as impasse depth increases, with help-seeking impasses declining most sharply — related