Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models

ArXi:2605.25230v1 Announce Type: new Recent work on recursive architectures has shown that tiny neural networks can be surprisingly powerful on structured reasoning tasks. The trick is to model reasoning trajectories with a latent dynamical system. We argue that the inference-time behaviour of these architectures is best understood as approximate inference over latent reasoning trajectories, with deterministic recursion as the one-particle, zero-noise limit.