When to Re-Plan: Subgoal Persistence in Hierarchical Latent Reasoning

Long-horizon reasoning requires a system to commit to medium-horizon intent without becoming rigid: re-plan too often and computation never coheres into multi-step structure; commit too long and the plan goes stale. We study this stability–adaptivity tradeoff in the latent reasoning setting, where multi-step computation occurs inside hidden state rather than externalized token traces. We extend the Hierarchical Reasoning Model (HRM) with a feudal-style manager–worker interface: a slow high-level module periodically emits a normalized directional sub-goal that persists for P low-level steps, biasing the worker’s hidden-state updates and supplying an intrinsic cosine alignment loss. On ARC and ConceptARC, we find that subgoal persistence — not subgoal injection alone — is the central knob: moderate periods P ∈[3,6] consistently outperform both very frequent (P=1) and very long horizons, with a clear minimum LM loss at P=3 (1.544 vs. 1.674 at P=1, 1.640 baseline; replicated over 5 seeds at mean 1.595, std 0.045). The intrinsic alignment weight λ shows a complementary narrow optimum (λ≈0.05). A controlled ablation at past-sweet-spot λ isolates learned directional structure — not architectural capacity or auxiliary loss alone — as the source of interference when the alignment signal exceeds its optimum. Together these findings implicate a design principle for compositional planning in latent reasoning systems: medium-horizon intent must be coherent across enough computational steps for compositional structure to form.