Escape Rooms Inspire AI Models to Enhance VR and AR Learning Experiences

Over the past few years, virtual reality (VR) and augmented reality (AR) have gained traction in education, promising immersive, interactive learning experiences. However, a significant challenge remains: how to get students to reflect critically on what they’re learning without disrupting their engagement with the technology. Northeastern University researchers believe the solution may lie in an unlikely source: escape rooms. Escape rooms are interactive puzzle games where participants are locked in a themed room and must solve a series of challenges to escape within a set time limit. These rooms have become globally popular, not only for their entertainment value but also for the way they engage and challenge players. According to a study published in the Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems, escape room facilitators, or game masters (GMs), use techniques that could enhance VR and AR learning environments. Casper Harteveld, a professor of game design at Northeastern, led the research team. Instead of consulting traditional learning scientists, the team interviewed 13 escape room GMs to understand how they manage player experiences and problem-solving. The GMs' approach, which involves constant observation and tailored intervention, offers valuable insights into designing effective AI models for educational technology. One of the primary roles of a GM is to observe players through hidden cameras, ensuring they are progressing and finding clues. When players get stuck, GMs intervene by providing hints, a process known as "incremental scaffolding of aid." Initially, they offer vague clues and then gradually increase the specificity of the hints as needed. This method allows players to maintain their immersion while nudging them toward a solution. Erica Kleinman, a postdoctoral researcher on the project, explains that GMs are adept at gauging players' needs and emotional states. They use these cues to decide when and how to provide aid, ensuring that the assistance is both helpful and non-disruptive. Kleinman notes, "Escape rooms inherently already have a kind of reflective prompting built into them because you have the GM chiming in to help you. It feels natural to have somebody say, 'Hey, I noticed you're stuck. Have you thought about what you did last time that you were stuck?'" The GM's personalized and adaptive approach is crucial for immersive learning. Harteveld emphasizes, "Personalization, adaptation, that's where we want education to go, and escape room facilitators already do that." By understanding and emulating these techniques, the researchers aim to create AI models that can support students in VR and AR environments without giving away answers, fostering deeper learning and reflection. The team is currently developing an escape room to test their AI model. The goal is to create a supportive reflection tool that helps students think critically about their actions and progress. Harteveld highlights the importance of maintaining the sense of accomplishment: "Aid should make players feel like they came up with the solution themselves. It’s really empowering the players, and this is something you can translate to AI. You still want the humans to do the work." While the research focuses on enhancing educational VR and AR, its implications extend beyond the classroom. The insights gained from escape room GMs could reshape how we design AI to interact with humans in various contexts, promoting a collaborative and empowering relationship rather than a dependency on automated solutions. Industry insiders laud this approach, noting that it bridges the gap between theoretical educational models and practical, real-world applications. Companies like Google and Microsoft, which are heavily invested in immersive technologies, are closely watching the development of such adaptive AI systems. These systems could significantly enhance user engagement and learning outcomes, making VR and AR more effective and widely adopted in educational settings. Northeastern University, known for its innovative research in technology and education, is leading the charge in this interdisciplinary effort. With their focus on user-centered design and experiential learning, the university is poised to make groundbreaking contributions to the field. The research team’s next steps include refining their AI model and conducting extensive trials to validate its effectiveness in immersive learning environments.