An interdisciplinary team at North Carolina State University has developed an AI-based framework designed to help undergraduate students build stronger research questions, according to a report by Phys.org. The system, called Socratic Challenger, walks students through a structured process that uses AI not to answer questions for them, but to challenge the thinking behind the questions they are already forming.
The problem the tool aims to solve is one instructors have long recognized. Students can often name a topic they care about, but converting that interest into a workable, meaningful research question is harder than it sounds. At the same time, many undergraduates are already turning to AI for academic help, often without a clear goal in mind.
"Formulating a good research question is a bottleneck in undergraduate inquiry," said Aram Mikaelyan, corresponding author of the journal article describing the work and an associate professor of entomology at NC State. "Students can name topics they're interested in, but struggle to find ways to turn that interest into a meaningful research question that makes sense and can be developed into a research project."
Mikaelyan was direct about the limits of unsupervised AI use. "We also know that undergraduates are often turning to AI for assistance with academic work without having a clear idea of what is expected of them or what they are trying to accomplish, which is not helpful," he said. "So we developed a detailed, step-by-step workflow that allows students to use AI tools, requires students to think critically, and helps students develop research questions that can be used to enable undergraduate research."
The Socratic Challenger framework consists of eight steps. Five of those steps are AI-enabled. The process begins with identifying a topic of interest and moves through stages that include receiving feedback from peers and instructors. The AI's role throughout is not to generate answers, but to interrogate the student's own thinking.
"To be clear, the AI is not generating the research question," Mikaelyan said. "Instead, the AI is essentially being used to interrogate the student's process and help them develop the habits of mind necessary to think critically about research. Is this really a gap in what we know about the topic? Is this question novel? What resources would I need to address this question, methodologically? And so on."
Co-author Erin McKenney, an assistant professor in NC State's College of Agriculture and Life Sciences, pointed to the practical gap the tool is trying to fill. "Ideally, students could work with mentors to learn how to develop a meaningful research question — but that's not feasible given the number of students," McKenney said. "This framework, which we call Socratic Challenger, provides instructors with a new tool that can help to address that need."
To test whether Socratic Challenger actually worked, the researchers ran a proof-of-concept study with 45 students in an undergraduate ecology course. Students worked through the framework over nine weeks and were ultimately asked to submit an abstract for a proposed research project. The team wanted to evaluate not only whether the tool worked, but which steps were most effective and whether students felt it made a difference.
