The extent to which individual differences in cognitive abilities affect the relationship among task complexity, attention to form, and second language development has been addressed only minimally in the cognition hypothesis literature. The present study explores how reasoning demands in tasks and working memory (WM) capacity predict learners' ability to notice English question structures provided in the form of recasts and how this contributes to subsequent development of English question formation. Eighty-one nonnative speakers of English completed three interactive tasks with a native speaker interlocutor, one WM task, and three oral production tests. Prior to the first interactive task, participants were randomly assigned to a task group (simple or complex). During task performance, all learners were provided with recasts targeting errors in question formation. The results showed that learners' cognitive processes during tasks were in line with the cognitive demands of the tasks, at two complexity levels. The findings suggest that WM was the only significant predictor of the amount of noticing of recasts as well as of learners' question development. With regard to interaction effects between WM and task complexity, high WM learners who carried out a complex version of the tasks benefitted the most from task-based interaction.