Extrapolating User Preferences via Compositional Atomic State Transitions

Sequential recommendation models typically encode user dynamics as continuous latent vectors. However, these monolithic representations conflate distinct preference dimensions, limiting their ability to generalize compositionally to novel configurations of known elements. To address this, we propose $\text{C}$ompositional $\text{A}$tomic $\text{S}$tate $\text{T}$ransitions, a framework that reconceptualizes preference evolution as state transitions within a discrete, compositional semantic space. Rather than allowing unconstrained latent shifts, CAST decomposes user profiles into facet-specific semantic atoms and models temporal dynamics via typed atomic operations. This design constrains future extrapolation to recombinations of known atoms, yielding interpretable semantic trajectories and soft transition signals for downstream candidate ranking. To evaluate this capability, we introduce a temporal extrapolation protocol with strict chronological and combination holdouts, isolating compositional generalization from mere entity recognition. Experiments demonstrate that CAST recovers a non-trivial subset of unseen preference configurations and improves candidate ranking across multiple sequential backbones. Ultimately, CAST provides an interpretable inductive bias for modeling compositional user dynamics.