Reasoning Models Don't Just Think Longer, They Move Differently 事件

Reasoning Models Don't Just Think Longer, They Move Differently arXiv:2605.15454v2 Announce Type: replace Abstract: Reasoning-trained language models often spend more tokens on harder problems, but longer chains of thought do not show whether a model is merely computing for more steps or following a different internal trajectory. We study this distinction through hidden-state trajectories during chain-of-thought generation across competitive programming, mathematics, and Boolean satisfiability.