Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
Open paper
Benchmark
Model
Rank
Results
mathematical-reasoning-on-aime24
Qwen3-1.7B (student) via two-stage bridge from RL-trained Qwen3-8B teacher
–
Acc: 25.2
Rank counts only results with a code link.