Learning-Zone Energy: Online Data Selection for Efficient RL Post-Training

arXiv:2605.17003v2 Announce Type: cross Abstract: Reinforcement Learning (RL) post-training has emerged as the dominant paradigm for eliciting mathematical reasoning in Large Language Models (LLMs), yet prevailing techniques such as GRPO and DAPO distribute rollout and gradient budgets nearly uniformly across prompts, squandering compute on samples that are already mastered or remain far beyond the model's current capability. To address this fundamental inefficiency, we propose Learning-Zone Ene