Generative AI is reshaping education, and homework is at the center of this change. Tools like ChatGPT make it very tempting to bypass essential cognitive steps such as recalling concepts, re-elaborating ideas, and applying knowledge. These steps are not just formalities; they are the foundation of learning. When they disappear, so does much of the educational value of assignments.
Some institutions have responded by banning AI, but this approach is difficult to enforce and ignores the reality that AI will be part of students’ future professional environments. Instead, we believe the challenge is to integrate AI thoughtfully, in ways that preserve learning objectives, enhance pedagogical tools, and promote equity.
LLteacher is our attempt to do this. It is an open-source tool designed for homework assignments in statistics courses. Rather than providing direct answers, LLteacher guides students through problem-solving, encouraging active engagement and critical thinking. Instructors retain control over the scope and content, and they can review the full interaction between students and the AI, making the process transparent and pedagogically meaningful.
Our goal is not to replace traditional methods or promise a perfect solution. LLteacher is an initial step toward exploring how AI can support learning rather than undermine it. It enables approaches such as recall-based practice, discovery-driven assignments, and error-based learning, which are difficult to achieve with conventional homework formats.
We see LLteacher as part of an ongoing conversation about how education can adapt to the realities of AI. The code is openly available for instructors who wish to experiment, adapt, and share their experiences. This is a work in progress, and we expect to learn as much from its use as students do from interacting with it.
More details on the LLteacher are available in our paper, LLteacher: A Tool for the Integration of Generative AI into Statistics Assignments