Institution profile

digiLab

Research institution
Research library1linked papers
Opportunities0open roles
Selected work

Representative Papers

Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models

May 24, 2026

This work addresses the limited quality of reasoning trajectories generated by recursive models in structured reasoning tasks by proposing a training-free guided stochastic exploration framework. Treating recursive reasoning as approximate inference over implicit trajectories, the method generates neighboring trajectories through stochastic perturbations and dynamically reweights them using the model’s built-in early-stopping head. The study introduces three novel unsupervised diagnostic metrics—local stability, guidance alignment, and cloud token entropy—that enable prediction of method efficacy and result reliability solely from reasoning trajectories. Evaluated on Sudoku-Extreme, the approach boosts solution accuracy from 85.9% to 98.0%, and on Maze-Hard, it successfully identifies guidance misalignment issues, with predictions strongly corroborated by subsequent performance validation.

0 citationsRead paper
Recent publications

Latest Papers

Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models

May 24, 2026

This work addresses the limited quality of reasoning trajectories generated by recursive models in structured reasoning tasks by proposing a training-free guided stochastic exploration framework. Treating recursive reasoning as approximate inference over implicit trajectories, the method generates neighboring trajectories through stochastic perturbations and dynamically reweights them using the model’s built-in early-stopping head. The study introduces three novel unsupervised diagnostic metrics—local stability, guidance alignment, and cloud token entropy—that enable prediction of method efficacy and result reliability solely from reasoning trajectories. Evaluated on Sudoku-Extreme, the approach boosts solution accuracy from 85.9% to 98.0%, and on Maze-Hard, it successfully identifies guidance misalignment issues, with predictions strongly corroborated by subsequent performance validation.

0 citationsRead paper