HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning

ArXi:2605.05951v1 Announce Type: new World models enable model-based planning through learned latent dynamics, but imagined rollouts become unstable as the planning horizon grows or the dynamics distribution shifts. We argue that this instability reflects two missing structures in planner-facing latents: history-conditioned memory for approximate Marko completeness, and geometric organization that separates configuration, momentum, and task semantics.