AI RESEARCH
Modeling Hierarchical Thinking in Large Reasoning Models
arXiv CS.AI
•
ArXi:2510.22437v2 Announce Type: replace 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 (FSM) transitioning among six abstract cognitive states. We nstrate that these states and transitions can be captured in the latent state of the model.