Showing 2026Show all
2 papers · 1 filter
cs.AI2026
Mitigating Over-Optimization in PRM-Guided Search in Mathematical Reasoning by Optimizing the Guide
Taejong Joo, Diego Klabjan
Process reward models (PRMs) provide dense step-level guidance for search-based reasoning, enabling inference-time compute to be allocated toward promising partial solutions. Howev…
stat.ML2026
Model-based Bootstrap of Controlled Markov Chains
Ziwei Su, Imon Banerjee, Diego Klabjan
We propose and analyze a model-based bootstrap for transition kernels in finite controlled Markov chains (CMCs) with possibly nonstationary or history-dependent control policies, a…