Reflective Dialogue or Prompt Refinement? Effects of Tutor Scaffolding on Students' Independent LLM Use for Programming
For educators and designers of AI-based learning tools, this work shows that dialogic scaffolding (Socratic guidance) can foster deeper learning and better independent LLM use compared to prompt refinement, addressing concerns about superficial engagement with LLMs.
This study compared two LLM-based tutors (Socratic-Guidance vs. Prompt-Refinement) in a graduate robotics course, finding that Socratic guidance led to higher learning gains and more understanding-driven prompting strategies in subsequent unconstrained LLM use, despite being perceived as less efficient.
While Large Language Models (LLMs) can provide personalized support in learning, several studies have raised concerns regarding their use in education. Importantly, learning depends on how students engage with LLMs. This study examined how two types of LLM-based tutors shape students' prompting practices, learning, and subsequent LLM-use: a Socratic-Guidance (SG) tutor, which structures interaction through dialogic questioning, and a Prompt-Refinement (PR) tutor that guides the formulation of effective prompts. We conducted a two-phase study in a graduate-level mobile robotics course: 66 students used either the SG or PR tutor during a 6-week intervention, followed by 52 students using an unconstrained LLM during a 3-week course project. Results show that while the SG- and PR tutors led to similar task performance and prompting patterns during guided use, they differ in learning outcomes and later LLM-use. SG-students, relative to PR-student, achieved higher learning gains in later sessions, and were more likely to adopt understanding-driven prompting strategies, which are predictive of higher understanding, when using an unconstrained LLM. Although learners perceived the SG tutor as less efficient, the findings suggest that Socratic guidance supports the development of students' capacity to learn with LLMs over time, highlighting its importance for LLM tutor design.