Development of vocational education and training chatbot supported by large language model-based multi-agent system

Abstract

Vocational education and training (VET) chatbots face issues such as difficulties in competence development support, limitations in teaching decision-making, and defects in competence assessment methods. This study constructed an large language model (LLM)-based VET chatbot and designed a human-computer collaborative teaching model. It applied a quasi-experimental design to conduct a teaching experiment in a course titled Electronic Circuits and CAD Plate Making at a VET institution. Results showed that the LLM-based VET chatbot and its application model could significantly improve students' Level 1 and Level 2 professional competence (functional competence and processual competence according to COMET). It also discusses ideas for future optimization of the LLM-based VET chatbot.