Social insect groups, such as bees, termites, and ants, epitomize the emergence of group-level behaviors from the aggregated actions and interactions of individuals. Ants have the unique advantage that whole colonies can be observed in artificial, laboratory nests, and each individual's behavior can be continuously tracked using imaging software. In this dissertation, I study two group behaviors: (1) the spread of alarm signals from three agitated ants to a group of 61 quiescent nestmates, and (2) the reduction in per-capita energy use as colonies scale in size from tens of ants to thousands. For my first experiment, I track the motion of Pogonomyrmex californicus ants using an overhead camera, and I analyze how propagation of an initial alarm stimulus affects their walking speeds. I then build an agent-based model that simulates two-dimensional ant motion and the spread of the alarmed state. I find that implementing a simple set of rules for motion and alarm signal transmission reproduces the empirically observed speed dynamics. For the second experiment, I simulate social insect colony workers that collectively complete a set of tasks. By assuming that task switching is energetically costly, my model recovers a metabolic rate scaling pattern, known as hypometric metabolic scaling. This relationship, which predicts an organism's metabolic rate from its mass, is observed across a diverse set of social insect groups and animal species. The results suggest an explicit link between the degree of workers' task specialization and whole-colony energy use.