Reflective Dialogue or Prompt Refinement? Effects of Tutor Scaffolding on Students' Independent LLM Use for Programming
arXiv:2607.03303v1 Announce Type: new Abstract: 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
The proliferation of LLMs in education necessitates structured research into effective pedagogical integration and scaffolding methods to maximize learning outcomes.
Understanding how different LLM-based tutors influence student interaction, learning, and independent LLM use is crucial for developing responsible and effective AI in education.
This study contributes to a more nuanced understanding of optimal LLM tutoring strategies, moving beyond simple access to LLMs to focus on interaction design.
- · EdTech developers
- · Educators leveraging AI
- · Students with effective LLM guidance
- · AI research in education
- · Unstructured LLM deployment in education
- · Pedagogical approaches ignoring AI interaction
- · Students without proper LLM scaffolding
Research findings will inform the design of more effective AI-powered educational tools and platforms.
Improved LLM integration could lead to personalized learning at scale, reducing educational disparities.
A highly AI-augmented education system might reshape curriculum development and teacher roles, emphasizing meta-learning and prompt engineering skills.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.AI