Thinking About Thinking: Evaluating Reasoning in Post-Trained Language Models

arXiv:2510.16340v2 Announce Type: replace-cross Abstract: Recent advances in post-training techniques have endowed Large Language Models (LLMs) with enhanced capabilities for tackling complex, logic-intensive tasks through the generation of supplementary planning tokens. This development raises a fundamental question: Are these models aware of what they "learn" and "think"? To address this, we define three core competencies: (1) awareness of learned latent policies, (2) generalization of these p