SpikeWorld: Adapting Frozen World Models with Compact State

A world model can predict the future yet remain unable to absorb the errors revealed when that future arrives. We ask how much mutable state is needed to adapt its predictions without rewriting its learned representation. We introduce SpikeWorld, which pairs a next-event predictive–semantic model with a bounded external fast state. We separate the shared computation learned offline from the residual corrections written online: completed actions supervise later predictions, while a distinct score state calibrates registered action transformations. On a continual stream of registered actuator changes, 29 KB of mutable state obtains a 19.3% prequential prediction gain, versus 21.9% for prediction-path tuning with 67× more mutable state. Controlled formation tests establish temporal predictive structure, and a same-stream routed matrix RLS comparison provides a compact actuator-identification reference. SpikeWorld makes deployment plasticity explicit: retain the predictive representation, and allocate bounded state to what new observations teach.