Beyond the Commitment Boundary: Probing Epiphenomenal Chain-of-Thought in Large Reasoning Models

Excerpt

arXiv:2606.13603v2 Announce Type: replace Abstract: Chain-of-thought (CoT) reasoning is the dominant paradigm for inference-time scaling in language models, yet the causal influence of individual steps on the final answer remains poorly understood. In this work, we use answer logits at the end of each reasoning step to estimate each step's causal importance to the final answer and intermediate guesses, shedding light on the answer formation process of several reasoning model families. Across div