Learning from Your Own Mistakes: Constructing Learnable Micro-Reflective Trajectories for Self-Distillation
Open paper
Benchmark
Model
Rank
Results
mathematical-reasoning-on-aime-2025
Cold-start + TAPO (Qwen3-8B-Instruct)
–
Accuracy: 46.88
mathematical-reasoning-on-aime24
Cold-start + TAPO (Qwen3-8B-Instruct)
–
Acc: 62.50
Rank counts only results with a code link.