Evidence-Decision-Feedback: Theory-Driven Adaptive Scaffolding for LLM Agents

Abstract: Multi-agent LLM architectures offer opportunities for pedagogical agents to help students construct domain knowledge and develop critical-thinking skills, yet many operate on a "one-size-fits-all" basis, limiting their ability to provide personalized support. To address this, we introduce Evidence-Decision-Feedback (EDF), a theoretical framework for adaptive scaffolding using LLMs. EDF integrates elements of intelligent tutoring systems and agentic behavior by organizing interactions around evidentiary inference, pedagogical decision-making, and adaptive feedback. We instantiate EDF through Copa, an agentic collaborative peer agent for STEM+C problem-solving. In an authentic high school classroom study, we show that EDF-aligned interactions align feedback with students' demonstrated understanding and task mastery; promote gradual scaffold fading; and support interpretable, evidence-grounded explanations without fostering overreliance.