Design chatbots that begin with guided inquiry and progressively provide explicit guidance when students remain stuck¶

Strategy · All strategies
Evidence · no claims cited

Description¶

Based on the finding that combination-preferring students showed nominally more sophisticated epistemological beliefs, the authors recommend chatbots that "begin with questions, hints, or prompts for explanations and then progressively provide more explicit guidance if the student remains stuck." This approach is intended to balance productive struggle with timely support, preventing inquiry from becoming frustrating and preventing answer provision from inhibiting engagement in epistemic practices such as sensemaking.

Design Implications¶

Context¶

Requirements¶

• Custom-built chatbots capable of initiating Socratic-style questioning and escalating to direct answers on request or after sustained difficulty

Constraints¶

• The supporting association was not statistically significant after Bonferroni adjustment, so the authors frame the results as warranting further investigation

Target Learners¶

• introductory physics students

Target Learning Goals¶

• productive struggle, sensemaking, and sustained engagement in epistemic practices during physics problem solving

Related Strategies¶

• Chatbot support should reinforce that learning ability develops through effort, strategy use, feedback, and reflection
• Hybrid Socratic-to-sub-question tutoring with EEG-triggered fallback and progressively concrete hints

Examples¶

-

Key Sources¶

• Amogh Sirnoorkar and Omkar Mamidpalliwar. (2026). Students' Epistemological Beliefs and their Chatbot Preferences in AI-mediated Physics Learning. https://arxiv.org/abs/2607.29385