Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training

Benchmark Model Rank Results
mathematical-reasoning-on-mathverseQwen3-VL-4B + EPS (MMK12)–Accuracy: 55.1
multimodal-reasoning-on-mathvisionQwen3-VL-4B + EPS (MMK12)–Accuracy: 44.41
multimodal-reasoning-on-mmmu-proQwen3-VL-4B + EPS (MMK12)–Accuracy: 50.29