{"ID":5443827,"CreatedAt":"2026-07-01T02:07:11.383974684Z","UpdatedAt":"2026-07-03T15:30:41.833309164Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31846","arxiv_id":"2606.31846","title":"Z-1: Efficient Reinforcement Learning for Vision-Language-Action Models","abstract":"Vision-Language-Action (VLA) models offer a promising framework for robotic manipulation by connecting language instructions, visual observations, and continuous control. However, most existing policies remain limited by behavior cloning or supervised fine-tuning (SFT) from fixed demonstrations, which provides limited opportunity to improve from the policy's own failures. In this paper, we present Z-1, a reinforcement learning (RL) post-training framework for flow-based VLA models. Built on top of $π_{0.5}$, Z-1 uses only publicly released RoboCasa demonstrations for SFT and then applies a task-wise Group Relative Policy Optimization (GRPO) strategy across $24$ standard RoboCasa tasks. To improve the efficiency and stability of online optimization, Z-1 combines shared-prefix rollout construction, tree-structured trajectory branching, completion-aware reward calibration, and selective joint training of VLM and Action Expert. Across all $24$ RoboCasa tasks, Z-1 achieves an average success rate of $80.6\\%$, improving over its SFT initialization by $13.2\\%$ points and outperforms the published sota models. These results show that systematic GRPO post-training can substantially improve flow-based VLA policies without additional private demonstrations.","short_abstract":"Vision-Language-Action (VLA) models offer a promising framework for robotic manipulation by connecting language instructions, visual observations, and continuous control. However, most existing policies remain limited by behavior cloning or supervised fine-tuning (SFT) from fixed demonstrations, which provides limited...","url_abs":"https://arxiv.org/abs/2606.31846","url_pdf":"https://arxiv.org/pdf/2606.31846v1","authors":"[\"Lang Cao\",\"Renhong Chen\",\"Luyi Li\",\"Peng Wang\",\"Mofan Peng\",\"Yitong Li\"]","published":"2026-06-30T15:46:57Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}