RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning 事件

RLVR without Ineffective Samples: Group Prioritized Off-Policy Optimization for LLM Reasoning arXiv:2606.01281v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs). However, its effectiveness is substantially hindered by the prevalence of ineffective training data: many sampled prompts yield response groups that are either entirely correct or entirely inc