When Can Large Reasoning Models Save Thinking? Mechanistic Analysis of Behavioral Divergence in Reasoning

Understand

Large reasoning models (LRMs) have achieved remarkable success on complex tasks, yet their tendency to "overthink" leads to inefficiencies.

• Although "save-thinking" prompts are intended to mitigate this issue, we find that LRMs still frequently enter the "Still-thinking" mode instead of the expected "No-thinking" mode, especially on difficult queries.
• To analyze this behavioral divergence, we examine LRMs from three perspectives: confidence at the thinking-termination boundary, divergence in internal attention distributions, and attention allocation across prompt segments.
• We find that high perplexity is associated with later Still-thinking behavior, and that Still-thinking cases allocate more attention to the original question.