{"ID":2877693,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.19958","arxiv_id":"2508.19958","title":"Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulation","abstract":"Vision-Language-Action (VLA) models have become a cornerstone in robotic policy learning, leveraging large-scale multimodal data for robust and scalable control. However, existing VLA frameworks primarily address short-horizon tasks, and their effectiveness on long-horizon, multi-step robotic manipulation remains limited due to challenges in skill chaining and subtask dependencies. In this work, we introduce Long-VLA, the first end-to-end VLA model specifically designed for long-horizon robotic tasks. Our approach features a novel phase-aware input masking strategy that adaptively segments each subtask into moving and interaction phases, enabling the model to focus on phase-relevant sensory cues and enhancing subtask compatibility. This unified strategy preserves the scalability and data efficiency of VLA training, and our architecture-agnostic module can be seamlessly integrated into existing VLA models. We further propose the L-CALVIN benchmark to systematically evaluate long-horizon manipulation. Extensive experiments on both simulated and real-world tasks demonstrate that Long-VLA significantly outperforms prior state-of-the-art methods, establishing a new baseline for long-horizon robotic control.","short_abstract":"Vision-Language-Action (VLA) models have become a cornerstone in robotic policy learning, leveraging large-scale multimodal data for robust and scalable control. However, existing VLA frameworks primarily address short-horizon tasks, and their effectiveness on long-horizon, multi-step robotic manipulation remains limit...","url_abs":"https://arxiv.org/abs/2508.19958","url_pdf":"https://arxiv.org/pdf/2508.19958v2","authors":"[\"Yiguo Fan\",\"Pengxiang Ding\",\"Shuanghao Bai\",\"Xinyang Tong\",\"Yuyang Zhu\",\"Hongchao Lu\",\"Fengqi Dai\",\"Wei Zhao\",\"Yang Liu\",\"Siteng Huang\",\"Zhaoxin Fan\",\"Badong Chen\",\"Donglin Wang\"]","published":"2025-08-27T15:12:03Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[]","has_code":false}