A Theory of Adaptive Scaffolding for LLM-Based Pedagogical Agents

2025-08-02

AI Summary

Current LLM-based teaching agents (e.g., ChatGPT) lack grounding in learning science theories, limiting their pedagogical efficacy in STEM+C classrooms. Method: This study proposes the first adaptive scaffolding framework integrating Evidence-Centered Design (ECD) and Social Cognitive Theory to enable theory-driven, personalized instructional interactions and formative assessment. Cognitive principles are deeply embedded into the LLM agent’s architecture to establish an interpretable, verifiable human–AI collaborative intelligence mechanism—implemented as the Inquizzitor system. Contributions/Results: (1) It establishes a theoretical anchor for LLM applications in education; (2) it enables dynamic, learning-science-aligned scaffolding and feedback; and (3) empirical evaluation demonstrates significant improvements in instructional interaction quality and student experience, with strong endorsement from frontline educators.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures
• Machine Learning: Causal Learning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

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 illustrate this framework with Inquizzitor, an LLM-based formative assessment agent that integrates human-AI hybrid intelligence and provides feedback grounded in cognitive science principles. Our findings show that Inquizzitor delivers high-quality assessment and interaction aligned with core learning theories, offering teachers effective guidance that students value. This research underscores the potential for theory-driven LLM integration in education, highlighting the ability of these systems to provide adaptive and principled instruction.

Problem

• Lack of theoretical foundation in LLM-based classroom agents
• Need for adaptive scaffolding in STEM+C learning agents
• Integrating cognitive science principles in AI feedback systems

Innovation

• Combines Evidence-Centered Design with Social Cognitive Theory
• Integrates human-AI hybrid intelligence for feedback
• Provides adaptive and principled STEM+C instruction