ProPACT: A Proactive AI-Driven Adaptive Collaborative Tutor for Pair Programming

TL;DR

ProPACT is an AI-driven collaborative tutor that predicts and enhances pair programming collaboration by providing proactive, minimally intrusive scaffolds based on multimodal dyadic models.

Contribution

It introduces a novel proactive adaptive system that models and forecasts collaboration states to improve pair programming effectiveness.

Findings

ProPACT significantly improves debugging success and task efficiency.

Proactive feedback increases collaboration quality as measured by JVA and JME.

The system demonstrates effective real-time prediction of collaboration states up to 30 seconds ahead.

Abstract

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.