# Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in Frontier Models > Source: > Published: 2026-09-24 13:30:00+00:00 The rapid capability gains of frontier language models are widely attributed to improved reasoning abilities, yet this cannot be verified as raw CoT traces in closed-source systems are hidden. By registering a simple custom tool through a standard API feature, we induce frontier models to externaliz