Mechanisms of Misgeneralization in Physical Sequence Modeling

ArXi:2605.20299v1 Announce Type: new Generative sequence models are often trained to plan motion in physical domains, from robotics to mechanical simulations. When constructing a dataset to train such a model, engineers may curate nstrations to specify how trajectories should be distributed over a physical quantity like travel distance or mechanical energy. For example, a roboticist building a maze navigation agent might choose nstrations whose travel distances cover a fixed range uniformly, hoping to constrain the agent's expected power usage.