Designing child-centric AI learning environments: Insights from an LLM-powered creative project-based learning study

Creative PBL is Project-Based Learning (PBL) focused on developing creative solutions to real-world challenges, enhancing students’ creative performance. Large language models (LLMs) have been proven to assist in creative tasks, yet much controversy exists regarding their role in empowering children’s creative PBL. This paper explores the potential of LLMs in creative PBL settings, with a special focus on fostering creative learning. To get a context-enriched perspective from both students and mentors, we designed and conducted an LLM-powered creative PBL study and collected real learning process data as well as post-learning interview data. We began with a exploratory observation involving 12 middle school students and identified five design considerations for LLM applications in PBL. Building on this, we developed an LLM-powered, 48-hour PBL program and conducted a study with 31 middle school students. The findings of the multi-stakeholders’ interview indicated that LLMs can enhance every stage of PBL. Additionally, we also discovered ambivalent perspectives among students and mentors toward LLM usage. Furthermore, we explored the challenges and design implications of integrating LLMs into PBL and reflected on the program. By bridging AI advancements into educational practice, our work aims to inspire further discourse and investigation into harnessing AI’s potential in child-centric educational settings.