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

arXiv:2505.15276 · cs.AI, cs.CL · Submitted 2025-05-21 · Read on arXiv

cs.AI, cs.CL

Submitted: 2025-05-21

Updated: 2026-09-02

Terminology

• Accuracy — 29× in this paper · explained in 1 episode
• Thinking mode — 26× in this paper · explained in 2 episodes
• Reinforcement Learning — 5× in this paper · explained in 4 episodes
• Clustering — 4× in this paper · explained in 2 episodes
• Fine-Tuning — 4× in this paper · explained in 5 episodes
• Benchmark — 2× in this paper · explained in 2 episodes
• Consistency — 2× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 2× in this paper · explained in 6 episodes
• Reinforcement Learning (RL) — 2× in this paper · explained in 25 episodes
• Structured Reasoning — 2× in this paper · explained in 3 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Chain-of-Thought (CoT) — 1× in this paper · explained in 4 episodes
• Supervised Fine-Tuning (SFT) — 1× in this paper · explained in 8 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
• Training Verifiers to Solve Math Word Problems
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning
• Mathify: Evaluating Large Language Models on Mathematical Problem Solving Tasks
• Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
• DeepSeek-V3 Technical Report
• The Ultimate Guide to Fine-Tuning LLMs from Basics to Breakthroughs: An Exhaustive Review of Technologies, Research, Best Practices, Applied Research Challenges and Opportunities
• Optimizing Test-Time Compute via Meta Reinforcement Fine-Tuning
• Token-Budget-Aware LLM Reasoning
• Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
• Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
• Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models
• Syzygy of Thoughts: Improving LLM CoT with the Minimal Free Resolution
• Thought Manipulation: External Thought Can Be Efficient for Large Reasoning Models
• Chain of Draft: Thinking Faster by Writing Less
• Qwen2.5 Technical Report
• Reasoning Models Can Be Effective Without Thinking
• Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoning
• s1: Simple test-time scaling

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection