AGWM: Affordance-Grounded World Models for Environments with Compositional Prerequisites

ArXi:2605.06841v1 Announce Type: new In model-based learning, the agent learns behaviors by simulating trajectories based on world model predictions. Standard world models typically data, the model tends to internalize this correlation as a general causal rule while ignoring action preconditions. In interactive environments, however, agent actions can reshape the future affordance space. At each timestep, an action may becomes executable only after its prerequisites are met, or non-executable when they are destroyed. We term such events structure-changing events (SC events.