An Agent-Based Simulation Framework for ADHD: Modeling Attention Regulation and Adaptive Therapeutic Interventions

ADHD involves fluctuating attention, impulsivity, and reward sensitivity, varying across individuals and contexts. Current interventions are often generic, overlooking this heterogeneity. This paper introduces a simulation-based framework for modeling attentional regulation and evaluating interventions with Adaptive Therapeutic Interfaces (ATIs), which personalize support based on cognitive dynamics. The framework uses empirically grounded parameters for attention, inhibition, reward sensitivity, and temporal discounting across ADHD subtypes. Agent-based simulations model attentional fluctuations, hyperfocus, and responses to Just-in-Time Adaptive Interventions (JITAIs). Validation against meta-analytic benchmarks achieved an 87.5% pass rate, replicating realistic error patterns. Three experiments (N=50 per condition) showed state-responsive strategies outperformed fixed-timing ones by 9.9-14.1% versus 2.0-3.0% (p < .001). State-responsive interventions demonstrated superior scalability, with 86.5% universality versus 69.5% and broader coverage. Personalized intensity provided additional benefits for profiles with lower baseline capacity (+5.7%). The findings highlight that adaptive timing outperforms fixed schedules by 4-5×, that intensity should inversely relate to baseline capacity, and that state-responsive approaches cover more of the population. By modeling ADHD as a dynamic regulation system rather than a static deficit, this framework enables rapid, interpretable testing of personalized strategies without costly pilot studies, guiding the development of human-centred, neurodiversity-affirming ATIs that enhance engagement, safety, and learning, advancing evidence-based mental health applications.