Scaffold question formulation and active help-seeking in AI-supported tutoring systems¶

Strategy · All strategies
Evidence · no claims cited

Description¶

Based on observed differences in inquiry behavior, the article recommends that "AI-supported tutoring systems may benefit from scaffolding mechanisms that en- courage students to formulate questions and engage in more active help-seeking behaviors." This targets students who under-ask or rely on confirmation-seeking, and environments that encourage "reflective inquiry and pro- ductive help-seeking rather than repeated confirmation-seeking or excessive procedural delegation."

Design Implications¶

Context¶

Requirements¶

• The AI system must log or detect students' inquiry patterns so that scaffolding can encourage question formulation where help-seeking is passive or confirmatory.

Constraints¶

• The recommendation arises from a study where the two sessions differed in both programming topics and conceptual complexity, and the authors state findings should be interpreted cautiously.

Target Learners¶

• First-generation and novice CS2 students interacting with AI assistants

Target Learning Goals¶

• Productive help-seeking and reflective inquiry during programming problem solving

Related Strategies¶

• GenAI learning interfaces should actively scaffold monitoring, evaluation, and AI-shaping behaviors adolescents may not bring to the interaction on their own
• Encouraging Help-Seeking Behavior
• Help Seeking
• Embed metacognitive scaffolds in GenAI search systems — prompting sub-question formulation, guiding output comparison, and encouraging reflection on AI-user knowledge discrepancies
• Embed the KWL strategy across inquiry phases to guide question generation and question-quality monitoring
• Provide explicit prompting instruction and expert scaffolding before or during novice LLM activities
• Support children's ecological active learning through explanation prompts, active control, and environment design rather than explicit strategy training

Examples¶

-

Key Sources¶

• Matin Amoozadeh and Amin Alipour. (2026). Analysis of Types of Inquiries in Student-AI Interaction: A case study of two CS2 tasks. https://arxiv.org/abs/2608.17919