How may controlled breathing be beneficial, or detrimental to behavior? Computational process models are useful to specify the potential mechanisms that lead to behavioral adaptation during different breathing exercises. We present a physio-cognitive model of slow breathing implemented within a hybrid cognitive architecture, ACT-R/Φ. Comparisons to data from an experiment indicate that the physiological mechanisms are operating in a manner that is consistent with actual human function. The presented computational model provides predictions of ways that controlled breathing interacts with mechanisms of arousal to mediate cognitive behavior. The increasing use of breathing techniques to counteract effects of stressors makes it more important to have a detailed mechanistic account of how these techniques may affect behavior, both in ways that are beneficial and detrimental. This multi-level understanding is useful for adapting to changes in our physical and social environment, not only for performance, but for physical and mental health.