Intelligent Tutoring Systems for Leveraging Manufacturing Practical Skill Development

The emergence of large language models (LLMs) has opened new opportunities for leveraging artificial intelligence (AI) in evaluating learning progress. However, their practical application in educational diagnostics is hindered by challenges in dynamically collecting and processing learner data. To address these limitations, this study presents an innovative diagnostic framework powered by LLMs, designed to enhance collaborative learning through AIdriven tutor interactions. The system features two specialized agents: a learner agent that evaluates learning patterns and conducts initial diagnostics, and a second LLMbased agent that integrates tutoring guidelines with students' online learning data to create contextually relevant, simulated dialogues between tutors and students. The framework has shown high accuracy in tracking progress and delivering detailed differential diagnoses, representing a significant step forward in AIenabled educational diagnostics. This approach highlights the potential of AI to transform personalized learning by providing more precise and accessible support within tutoring environments.