Meta-procedural requests are prominent in student discourse with a Socratic AI tutor: Next Step Guidance is the second-most common discourse move despite the tutor being designed not to direct students¶

Claim · All claims
Evidence · 1 study · qualitative r2 · q2
Currency · newest study 2026 · checked against its sources 2026-10-20 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q2 i? A band of meta-procedural turns in which students ask the tutor what to do — Next Step Guidance (4.4%, the second-largest category overall), Requesting Solution Help (1.6%), Asking for Principles (1.5%), Assumptions About Problem (1.3%) — is among the most striking features of the taxonomy. → Syed Furqan Abbas Hashmi and N. Sanjay Rebello 2026

Evidence¶

Syed Furqan Abbas Hashmi and N. Sanjay Rebello 2026¶

Syed Furqan Abbas Hashmi and N. Sanjay Rebello. (2026). A bottom-up taxonomy of student discourse with a Socratic AI physics tutor. https://arxiv.org/abs/2608.07373 doi:10.48550/arxiv.2608.07373

q2 · i? · qualitative · r2

Observational frequency analysis of the 2,874-turn corpus from 221 sessions. The article reports "Next Step Guidance(4.4%, the second-largest category overall)" within a band of requests for the tutor to supply the next strategic move. No effect size is printed.

"A second large band consists of turns in which the student does not advance the problem themselves but instead asks the tutor what to do:Next Step Guidance(4.4%, the second-largest category overall)"

Discussion¶

Related Claims¶

• Student discourse with a Socratic AI physics tutor concentrates sharply: of 357 consolidated categories, the top 25 cover roughly half of all student turns — a broader claim this one bears on
• Equation-handling and symbolic execution dominate the head of the student-discourse distribution, with roughly a third of top-20 turns involving equation work — related
• Grade-9 students' LLM-supported mathematical interactions are strongly request-dominated, with little explicit planning, monitoring, or evaluation — a broader claim this one bears on
• Students' questions shift from broad to specific during Socratic AI tutoring, from about 10–15% specific in the first turn to all students asking specific questions by the final turn — related
• The top of the student-discourse distribution contains essentially no categories of explicit conceptual reasoning, prediction, comparison to similar problems, or critical engagement with the tutor's suggestions — related
• During AI-tutor interactions, students' turns were dominated by help requests with near-absent monitoring and evaluation — a broader claim this one bears on
• Students' help requests to the AI tutor were predominantly instrumental rather than executive, with procedural content and low verification — related
• Student chat questions in the pilot were distributed across seven categories, dominated by study strategies (23%), conceptual quantum (20%), and mathematical formalism (17%) — related
• AutoTutor cannot handle most student questions, so student question frequency extinguishes quickly in tutoring sessions — related