In the evolving landscape of higher education, challenges such as the COVID-19 pandemic have underscored the necessity for innovative teaching methodologies. These challenges have catalyzed the integration of technology into education, particularly in blended learning environments, to bolster self-regulated learning (SRL) and higher-order thinking skills (HOTS). However, increased autonomy in blended learning can lead to learning disruptions if issues are not promptly addressed. In this context, OpenAI's ChatGPT, known for its extensive knowledge base and immediate feedback capability, emerges as a significant educational resource. Nonetheless, there are concerns that students might become excessively dependent on such tools, potentially hindering their development of HOTS. To address these concerns, this study introduces the Guidance-based ChatGPT-assisted Learning Aid (GCLA). This approach modifies the use of ChatGPT in educational settings by encouraging students to attempt problem-solving independently before seeking ChatGPT assistance. When engaged, the GCLA provides guidance through hints rather than direct answers, fostering an environment conducive to the development of SRL and HOTS. A randomized controlled trial (RCT) was employed to examine the impact of the GCLA compared to traditional ChatGPT use in a foundational chemistry course within a blended learning setting. This study involved 61 undergraduate students from a university in Taiwan. The findings reveal that the GCLA enhances SRL, HOTS, and knowledge construction compared to traditional ChatGPT use. These results directly align with the research objective to improve learning outcomes through providing guidance rather than answers by ChatGPT. In conclusion, the introduction of the GCLA has not only facilitated more effective learning experiences in blended learning environments but also ensured that students engage more actively in their educational journey. The implications of this study highlight the potential of ChatGPT-based tools in enhancing the quality of higher education, particularly in fostering essential skills such as self-regulation and HOTS. Furthermore, this research offers insights regarding the more effective use of ChatGPT in education.

In the field of Science, Technology, Engineering, and Mathematics (STEM) education, which aims to cultivate problem-solving skills, accurately assessing learners' engagement remains a significant challenge. We present a solution to this issue with the Real-time Automated STEM Engagement Detection System (RASEDS). This innovative system capitalizes on the power of artificial intelligence, computer vision, and the Interactive, Constructive, Active, and Passive (ICAP) framework. RASEDS uses You Only Learn One Representation (YOLOR) to detect and map learners' interactions onto the four levels of engagement delineated in the ICAP framework. This process informs the system's recommendation of adaptive learning materials, designed to boost both engagement and self-efficacy in STEM activities. Our study affirms that RASEDS accurately gauges engagement, and that the subsequent use of these adaptive materials significantly enhances both engagement and self-efficacy. Importantly, our research suggests a connection between elevated self-efficacy and increased engagement. As learners become more engaged in their learning process, their confidence is bolstered, thereby augmenting self-efficacy. We underscore the transformative potential of AI in facilitating adaptive learning in STEM education, highlighting the symbiotic relationship between engagement and self-efficacy.