Leveraging an LLM-Driven Feedback System to Support Computational Thinking and AI-Integrated STEM LearningK12
As artificial intelligence (AI) becomes increasingly embedded in scientific and technical domains, the ability to engage in AI-integrated STEM problem-solving is emerging as a critical skill for the future STEM workforce. Supporting students in this type of problem-solving requires building a strong foundation in computational thinking, particularly through pedagogically effective and technically robust tools. In this paper, we propose augmenting XXXXX, a block-based programming environment designed for AI-integrated STEM problem-solving, with large language model-driven feedback capabilities to facilitate students’ problem-solving while reinforcing key computational thinking skills for middle-grade students. We prompt a large language model with structured knowledge about breadth-first search to provide contextualized, adaptive feedback. The LLM helps students connect their problem-solving steps to the high-level structure of the breadth-first search algorithm and apply this understanding to pathfinding. We present a proof-of-concept evaluation that demonstrates the potential of the system to support the development of computational thinking through AI-integrated problem solving in diverse STEM contexts.