Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models

May 24, 2026 Β· Grace Period Β· πŸ› the proceedings of the ICML 2026 Workshop on Structured Probabilistic Inference & Generative Modeling

⏳ Grace Period
This paper is less than 90 days old. We give authors time to release their code before passing judgment.
Authors Andrew Corbett, Archit Sood, Anna Tzatzopoulou, Sai-Aakash Ramesh, Tim Dodwell arXiv ID 2605.25230 Category cs.AI: Artificial Intelligence Citations 0 Venue the proceedings of the ICML 2026 Workshop on Structured Probabilistic Inference & Generative Modeling
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 deterministic recursion as the one-particle, zero-noise limit. We make this view operational through guided stochastic exploration: stochastic perturbations of the reasoning dynamics propose neighbouring trajectories, and the model's existing early-stopping head reweights them online. The framework yields three label-free diagnostics: local stability, guide alignment, and cloud-token entropy. These predict, from inference traces alone, whether the procedure will help and which of its outputs to trust. On Sudoku-Extreme it lifts exact-solve accuracy from $85.9\%$ to $98.0\%$ without retraining; on Maze-Hard the diagnostics flag a misaligned guide, as validation performance later confirms. The same machinery thus characterises both when recursive reasoning has room to improve at the trajectory level and when the model's internal guide can recover it.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Artificial Intelligence