Evolutionary Reinforcement Learning based AI tutor for Socratic Interdisciplinary Instruction

This paper proposes ERL4SIIP, an evolutionary reinforcement learning framework for AI tutoring that uses Socratic questioning to teach STEM interdisciplinary concepts, specifically designed to avoid cognitive offloading by promoting active knowledge construction rather than direct answer delivery. The system explicitly addresses the 'spoon-feeding trap' and evaluates pedagogical quality through measures of knowledge integration, transfer, and strategic diversity.

Cultivating higher-order cognitive abilities -- such as knowledge integration, critical thinking, and creativity -- in modern STEM education necessitates a pedagogical shift from passive knowledge transmission to active Socratic construction. Although Large Language Models (LLMs) hold promise for STEM Interdisciplinary education, current methodologies employing Prompt Engineering (PE), Supervised Fine-tuning (SFT), or standard Reinforcement Learning (RL) often fall short of supporting this parad

Source

Framework Categories

Tool Types

Tags