A Theory of Adaptive Scaffolding for LLM-Based Pedagogical Agents

This paper presents a theoretical framework integrating Evidence-Centered Design with Social Cognitive Theory for adaptive scaffolding in LLM-based pedagogical agents, and demonstrates it through Inquizzitor, an LLM-based formative assessment agent tested with 104 middle school students in Earth Science STEM+C curriculum. The study evaluates the agent's scoring accuracy, interaction quality aligned with learning theories, and student perceptions of its value.

Large language models (LLMs) present new opportunities for creating pedagogical agents that engage in meaningful dialogue to support student learning. However, the current use of LLM systems like ChatGPT in classrooms often lacks the solid theoretical foundation found in earlier intelligent tutoring systems. To bridge this gap, we propose a framework that combines Evidence-Centered Design with Social Cognitive Theory for adaptive scaffolding in LLM-based agents focused on STEM+C learning. We ill

Study Type

Source

Framework Categories

Tool Types

Tags