Abstract
Adaptive learning systems increasingly employ pedagogical agents (PAs) to enhance students' engagement and learning outcomes, yet little is known about how motivational PAs influence students' conceptual understanding and strategic choice-making. This study compared 49 school students (at 9th and 10th grade) using an adaptive algebra learning environment with either motivational PAs or instructional prompts (non-PAs). Results revealed that while all students demonstrated learning gains, prior knowledge significantly moderated outcomes. Lower-knowledge students achieved the greatest gains through reflective engagement with foundational tasks, whereas higher-knowledge students often adopted intuitive but error-prone strategies. Notably, process mining and lag sequential analysis revealed distinct choice-making trajectories, uncovering how motivational PAs influenced self-regulation patterns over time. This study advances the field by operationalizing choice-making as a measurable self-regulated learning construct and reframing strategic disengagement as an adaptive, agentic behavior. Findings underscore the importance of designing adaptive systems that support both content mastery and strategic choice-making.