MazeMate: An LLM-Powered Chatbot to Support Computational Thinking in Gamified Programming Learning
This addresses the challenge of supporting computational thinking development for students in programming education, though it is incremental as it builds on existing gamified environments and LLM applications.
The researchers tackled the problem of fostering computational thinking (CT) in gamified programming learning by developing MazeMate, an LLM-powered chatbot embedded in a 3D maze game, and found that in a classroom study with 247 undergraduates, students rated it as moderately helpful, with higher perceived usefulness for maze solving than maze design.
Computational Thinking (CT) is a foundational problem-solving skill, and gamified programming environments are a widely adopted approach to cultivating it. While large language models (LLMs) provide on-demand programming support, current applications rarely foster CT development. We present MazeMate, an LLM-powered chatbot embedded in a 3D Maze programming game, designed to deliver adaptive, context-sensitive scaffolds aligned with CT processes in maze solving and maze design. We report on the first classroom implementation with 247 undergraduates. Students rated MazeMate as moderately helpful, with higher perceived usefulness for maze solving than for maze design. Thematic analysis confirmed support for CT processes such as decomposition, abstraction, and algorithmic thinking, while also revealing limitations in supporting maze design, including mismatched suggestions and fabricated algorithmic solutions. These findings demonstrate the potential of LLM-based scaffolding to support CT and underscore directions for design refinement to enhance MazeMate usability in authentic classrooms.