This randomized, controlled study examined the initial efficacy of an executive function training program for children with autism spectrum disorder. Seventy 7- to 11 year-olds with autism spectrum disorder and intelligence quotients [greater than or equal to]80 were randomly assigned to receive a web-based set of executive function training games combined with in-person metacognition coaching or to a waitlist. Primary outcomes were evaluated for neural responses related to executive function, lab-based executive function behavior, and generalization of executive function skills. Secondary outcomes included measures of social function. Post-testing and analyses were conducted by staff naïve to group assignment. Children exhibited a change in neural response following training relative to the waitlist group ([eta][subscript p][superscript 2]=0.14). Training effects were not detected via lab-based tasks ([eta][subscript p][superscript 2]s<0.02) or generalized to caregiver-reported executive function skills outside the lab ([eta][subscript p][superscript 2]=0.0001). However, the training group demonstrated reduced symptoms of repetitive behavior ([eta][subscript p][superscript 2]<0.015) following training. There were no adverse events or attrition from the training group. Findings suggest that brief, targeted computer-based training program accompanied by coaching is feasible and may improve neural responses and repetitive behaviors of school-aged children with autism spectrum disorder.