Characterizing the role of reasoning tokens in large language models as state over tokens
Nature Machine Intelligence, Published online: 07 October 2026; doi:10.1038/s42256-026-01303-y When large language models ‘reason’ about a problem, they might still solve it differently from what their reasoning transcript suggest. In this Perspective, Levy et al. describe how one can start investigating the role of these reasoning tokens.
We haven't written up this one. Nature Machine Intelligence has the full story — the link below goes straight to it.
