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

ACL ARR 2025 May Submission3380 Authors

Abstract: Large reasoning models (LRMs) have significantly advanced performance on complex tasks, yet their tendency to overthink introduces inefficiencies. This study investigates the internal mechanisms of reinforcement learning (RL)-trained LRMs when prompted to save thinking, revealing three distinct thinking modes: no thinking (NT), explicit thinking (ET), and implicit thinking (IT). Through comprehensive analysis of confidence in thinking termination, attention from thinking to generation, and attentional focus on input sections, we uncover key factors influencing the reasoning behaviors. We further find that NT reduces output length at the cost of accuracy, while ET and IT maintain accuracy with reduced response length. Our findings expose fundamental inconsistencies in RL-optimized LRMs, necessitating adaptive improvements for reliable efficiency.

Paper Type: Long

Research Area: Interpretability and Analysis of Models for NLP

Research Area Keywords: Probing,Calibration/uncertainty

Contribution Types: Model analysis & interpretability

Languages Studied: English

Submission Number: 3380