DAST: Difficulty-Adaptive Slow Thinking for Large Reasoning Models

ACL2025 SLM

O1-Pruner: Length-Harmonizing Fine-Tuning for O1-Like Reasoning Pruning

L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning

When More is Less: Understanding Chain-of-Thought Length in LLMs

Efficient Long CoT Reasoning in Small Language Models