Widely prescribed as the first choice of treatment for Attention-Deficit/Hyperactivity Disorder (ADHD), stimulants (methylphenidate and amphetamines) have been studied for their long-term effects on the brain in prospective designs that carefully control dosage and adherence. It is unknown whether those findings generalize to real-world conditions such as community-based treatment, which is marked by intermittent exposure and polypharmacy. To fill this gap, we capitalized on the observational design of the Adolescent Brain Cognitive Development (ABCD) study to examine effects of stimulant exposure on modulation of large-scale bilateral cortical networks’ resting-state functional connectivity (rs-FC) with 6 striatal regions (left and right caudate, putamen, and nucleus accumbens) across two years in children with ADHD. Out of 11,878 children, 179 met criteria for an ADHD diagnosis at baseline and high-quality imaging data at baseline and the two-year timepoint. Bayesian hierarchical logistic regressions revealed that change in rs-FC over the two-year period of multiple striatal-cortical networks associated with executive functions and a visuo-motor network predicted stimulant exposure. These networks did not overlap with those that predicted non-stimulant exposure. Of these networks, change selective to stimulant exposure was limited to rs-FC with the putamen, specifically frontoparietal and visual networks, implicating motor control. 23% of stimulant-exposed children did not meet criterion for ADHD at the two-year timepoint, and they were distinguished by change in rs-FC between left putamen and frontoparietal network. Thus, while stimulant exposure for a two-year period under real-world conditions modulated striatal-cortical functional networks broadly, therapeutic effects of that exposure were limited in scale, to network connections relevant to motor control in a small subset of children.