ProPACT: A Proactive AI-Driven Adaptive Collaborative Tutor for Pair Programming
For researchers and practitioners in collaborative learning, this work introduces a forecast-driven approach to real-time regulation of pair programming, addressing a gap in proactive adaptivity for dyadic interactions.
ProPACT is a proactive AI tutor for pair programming that predicts suboptimal collaboration states up to 30 seconds ahead using multimodal dyadic models, and delivers adaptive scaffolds. In a study with 26 dyads, proactive feedback improved debugging success, task efficiency, feedback uptake, and post-intervention joint attention and mental effort.
Effective pair programming depends on coordination of attention, cognitive effort, and joint regulation over time, yet most adaptive learning systems remain individual-centric and reactive. This paper introduces ProPACT, a proactive AI-driven adaptive collaborative tutor that treats collaboration itself as the object of instruction. ProPACT constructs a multimodal dyadic learner model based on Joint Visual Attention (JVA), Joint Mental Effort (JME), and individual mental effort, and employs an XGBoost-based forecasting model to predict emerging suboptimal collaboration states up to 30 seconds in advance. These predictions drive a hierarchical adaptive policy that delivers minimally intrusive scaffolds while fading support during productive collaboration. A within-subject study with 26 pair-programming dyads shows that proactive feedback significantly improves debugging success, task efficiency, feedback uptake, and post-intervention gains in JVA and JME, demonstrating the potential of forecast-driven dyadic adaptivity for real-time collaborative learning regulation.