The development of large language models offers new possibilities for enhancing adaptive scaffolding of student learning in game-based learning environments. In this work, we present a novel framework for automatic plan generation that utilizes text-based representations of students' actions within a game-based learning environment, Crystal…

In cultural relic restoration learning, developing both knowledge proficiency and self-efficacy is essential for academic success and professional competency. However, conventional learning methods often lack interactive elements that support cognitive engagement and skill acquisition. To address this limitation, this study introduced a…

Background: STEM education aims to develop innovation and problem-solving skills through interdisciplinary learning, yet struggles to foster student engagement and interdisciplinary thinking. Whilst alternate reality games (ARGs) can boost motivation via game-based problem-solving, integrating large language models (LLMs) remains underexplored.…