Rural and underserved schools face persistent learning gaps that AI-powered tools promise to close.

AI-guided feedback boosted science inquiry outcomes more than any other condition tested.

A dashboard showing peer comparisons without support to act on it increased stress, not performance.

Students with full AI support leaned on it instead of peers, reducing cross-group collaboration.

Co-authored by Jessica Murphy, Kodie Curran, Hannah Feeney, and Michael Hogan.

Educational inequity is one of the most persistent problems in modern schooling, and rural schools tend to feel it most. Rural students consistently fall behind in science achievement and have fewer chances to pursue science careers later in life (Saw & Agger, 2021). Worse, the digital tools meant to narrow these gaps are often least accessible where they’re needed most (Wang, 2025). Large classes, overstretched teachers, and limited support leave these students without the individualized, timely guidance that shapes long-term success.

Could AI help close this gap?

As AI reaches more corners of our lives, a natural question arises: Could wider access to these tools help to close this gap? With its capacity for personalized support, real-time feedback, and learning analytics delivered at scale, AI looks like a genuine opportunity for change. But is it feasible in the settings that need it most? Does it hold up over time? And if it works, what does it mean for the social fabric of the classroom—for collective intelligence, peer collaboration, and the traditional pedagogical structures schools have relied on for generations?

Chen and colleagues (2026) put these questions to the test. Over a full semester, the researchers ran a quasi-experiment with 150 eighth-grade students in a rural Chinese school, comparing a hybrid intelligence model against other technological interventions during a science inquiry module.........

© Psychology Today