A hungry idea isn't the same as a good research question, and that gap has stumped countless college students. But a team of researchers in North Carolina has built a clever fix: an artificial intelligence framework called Socratic Challenger that helps undergraduates sharpen their fuzzy interests into real, testable research questions.
Here's the problem the team set out to solve. Many students can name topics they care about, but they struggle to turn that spark into a meaningful question that a lab or classroom could actually investigate. On top of that, said Aram Mikaelyan, an associate professor of entomology at North Carolina State University, undergraduates are increasingly turning to AI for help without a clear sense of what they're trying to accomplish. That blind use of tools, he says, "is not helpful."
So the researchers designed an eight-step workflow — five of those steps are powered by AI. The steps walk students from picking a topic all the way to getting feedback from their peers and instructors. Crucially, the AI doesn't hand out answers. Instead, it interrogates the student's own thinking. Is this really a gap in what we know? Is this question novel? What resources would I need to answer it? The AI acts as a challenger, not a ghostwriter.
"We wanted to know if Socratic Challenger works and whether some steps in the workflow work better than others," said Erin McKenney, an assistant professor at NC State and a co-author of the study. "We also wanted to know whether students feel like it makes a difference."
To find out, the team ran a proof-of-concept study with 45 students in an undergraduate ecology course. Over nine weeks, the students worked through the framework and finished by submitting an abstract for a proposed research project. The results were encouraging: students who used the framework developed thoughtful research questions, and they valued every single step in the process.
"What we found is that the students who made use of the Socratic Challenger framework developed really thoughtful research questions," Mikaelyan said.
The bigger lesson, said co-author Dhvani Toprani of Elon University, is that technology alone doesn't teach understanding. But when it's wrapped in an intentional, step-by-step process, it genuinely boosts students' ability to learn and think critically.
The framework is designed to be forgiving and open-ended, which means it could work in messy, unstructured settings beyond a single classroom. The team hopes it might help students in other fields and other kinds of critical thinking — though they caution that educational tools depend on context, and more research is needed.
For now, the framework offers undergraduates something rare: a structured chance to have their ideas challenged early, before those ideas harden into projects. As co-author Olivia Mathieson, a Ph.D. student at NC State, put it: "Learning how to think critically about their own ideas in a structured way is a valuable skill."
The study appears in the journal Frontiers in Education.