Thought Branches: Interpreting LLM Reasoning Requires Resampling

arXiv:2510.27484v2 Announce Type: replace-cross Abstract: Most work interpreting reasoning models studies only a single chain-of-thought (CoT), yet these models define distributions over many possible CoTs. We argue that studying a single sample is inadequate for understanding causal influence and the underlying computation. Though fully specifying this distribution is intractable, we can measure a partial CoT's impact by resampling only the subsequent text. We present case studies using resampl