VLA-Tug：面向视觉-语言-动作模型的轻量级失败预测探针
Failure Prediction and Classification in Vision-Language-Action Models Via Calibrated Latent Probing
研究者给机器人 VLA 模型做了个潜层探针 VLA-Tug，能提前发现失败、还能预测失败原因，附带 3,180 条标注数据集。
VLA 模型在分布偏移下容易突发失败，可能损坏设备或危及人员。论文提出 VLA-Tug，一种叠加在 VLA 主干潜层上的轻量探针，可做早期失败检测、约束漏检与误报率，并预测失败模式以支持纠正动作。在相同误报率下，早期失败检出比最强学习基线提升最高 30%；在未见任务上，漏检与误报率边界在 86% 的运行中保持有效（基线最高仅 21%），失败模式预测的 top-3 准确率较多数基线提升最高 44%。作者还发布了一个包含 3,180 条带标注操作轨迹的数据集。
Failure Prediction and Classification in Vision-Language-Action Models Via Calibrated Latent Probing
Vision-Language-Action models (VLAs) enable general-purpose embodied intelligence, but their performance is brittle under distribution shift, where unanticipated failures can damage equipment or endanger people. Deploying VLAs in real-world systems therefore requires a runtime monitor that is timely, calibrated, and informative while being efficient enough to run on the edge. Existing methods fail to fulfill these requirements. We present VLA-Tug, a lightweight probe over the latent layers of a VLA backbone that improves early failure detection and bounds the missed-detection and false-alarm rates, with minimal inference overhead. We show that supervising on the pre-failure segment of a trajectory increases early failure detection at matched false-positive rates by up to 30% over the strongest learned baseline. Under shift to unseen tasks, the bounds on missed-detection and false-alarm rates remain valid in up to 86% of runs, versus at most 21% for baselines. Unlike existing methods, VLA-Tug predicts the failure mode to enable corrective actions, raising top-3 accuracy on unseen tasks by up to 44% over a majority baseline. VLA-Tug enables real-time monitoring where the well-timed and informative probe supports lightweight steering that improves task success. We release a dataset of 3,180 annotated manipulation episodes to support future work on latent failure detection in VLAs at https://vla-tug.github.io.