Manuel’s research interests address theories of agency (see https://manuelbaltieri.com/vision/), building a formal understanding of how agents, informally defined as autonomous systems acting on their environment to fulfil their goals can be described in a mathematical framework. His past work focused on the free energy principle and active inference, developing models of minimal agents, and studying their properties in the larger Bayesian framework advocated by these approaches. His current working hypothesis is that an autonomous system can be called an “agent” only if it models relevant parts of the environment while interacting with it. The existence of a meaningful way to describe agents and their environments as separate entities is however of paramount importance for this hypothesis. This involves a definition of boundaries, and especially of their origins: how does a system separate into coupled agent-environment subsystems? What are the (universal) principles that bring a system to do so? How do we describe this process mathematically? In his current work, Manuel is developing formal notion of internal/world models, studying their existence, necessary/sufficient conditions (e.g., agent-environment boundaries), and role in building a general theory of agency.