Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models
Open paper
Benchmark
Model
Rank
Results
mathematical-reasoning-on-minerva-math
DSR-7B with GPS
–
Accuracy: 39.7
mathematical-reasoning-on-olympiadbench
DSR-7B with GPS
–
Accuracy: 62.1
Rank counts only results with a code link.