[arXiv-2025] AdaptThink: Reasoning Models Can Learn When to Think

[arXiv-2025] OThink-R1: Intrinsic Fast/Slow Thinking Mode Switching for Over-Reasoning Mitigation

[arXiv-2025] ThinkPrune: Pruning Long Chain-of-Thought of LLMs via Reinforcement Learning

[arXiv-2025] Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models_

[arXiv-2025] Self-Training Elicits Concise Reasoning in Large Language Models

[arXiv-2025] CoT-Valve: Length-Compressible Chain-of-Thought Tuning

[arXiv-2025] O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning