Quantifying the Stability of Multi-Step Reasoning via Error Amplification

Excerpt

arXiv:2610.06404v1 Announce Type: cross Abstract: We consider the stability of multi-step reasoning processes, which have extensive applications in language models, including chain-of-thought and algorithmic reasoning. While longer sequences of reasoning can improve a model's generation capability at test time, the errors due to intermediate reasoning steps can accumulate in autoregressive generation, and thus grow substantially at the end. In this paper, we ask: What are the key factors determi