Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models 事件

Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models arXiv:2605.25230v1 Announce Type: new Abstract: 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 de