LLM Reasoning 思维链压缩 Pruning Long Chain-of-Thought of Large Reasoning Models via Small-Scale Preference Optimization TRAIN LONG, THINK SHORT：CURRICULUM LEARNING FOR EFFICIENT REASONING LAPO：INTERNALIZING REASONING EFFICIENCY VIA LENGTH-ADAPTIVE POLICY OPTIMIZATION Sample More to Think Less：Group Filtered Policy Optimization for Concise Reasoning Think in Blocks：Adaptive Reasoning from Direct Response to Deep Reasoning