Modeling Hierarchical Thinking in Large Reasoning Models 事件

Modeling Hierarchical Thinking in Large Reasoning Models arXiv:2510.22437v2 Announce Type: replace-cross Abstract: Large Reasoning Models (LRMs) solve complex tasks by generating long Chain-of-Thought (CoT) sequences; however, the emergent dynamics governing reasoning trajectories are not well understood and can lead to inconsistencies and reasoning pathologies. In this work, we propose to approximate LRM's emerging hierarchical reasoning dynamics as a trajectory within a Finite State Machine (