Saved in:
Bibliographic Details
Main Authors: Park, Seongheon, Li, Wendi, Oh, Changdae, Yeh, Samuel, Kira, Zsolt, Hagenow, Michael, Li, Sharon
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.30834
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911731126632448
author Park, Seongheon
Li, Wendi
Oh, Changdae
Yeh, Samuel
Kira, Zsolt
Hagenow, Michael
Li, Sharon
author_facet Park, Seongheon
Li, Wendi
Oh, Changdae
Yeh, Samuel
Kira, Zsolt
Hagenow, Michael
Li, Sharon
contents Vision-Language-Action (VLA) models enable robots to follow natural language instructions and generalize across diverse tasks, but they remain vulnerable to execution failures that compromise reliability in real-world deployment. Detecting such failures during execution is therefore critical for the robust deployment of embodied systems. Existing failure detection methods either rely on expensive action resampling or external models, while alternatives propagate trajectory-level labels uniformly across every timestep, obscuring localized failure signals. In this paper, we propose \textbf{Hide-and-Seek}, a framework that formulates VLA failure detection as a coarsely supervised learning problem. By combining inter-trajectory and intra-trajectory contrastive objectives, Hide-and-Seek localizes failure-indicative actions and induces temporally structured failure signals from trajectory-level supervision alone, without any step-level annotation. We evaluate Hide-and-Seek on LIBERO, VLABench, and a real-world robotic platform across three representative VLA policies: OpenVLA, $π_0$, and $π_{0.5}$.Our method achieves state-of-the-art multi-task failure detection performance with a practical accuracy--timeliness trade-off under conformal prediction, and generalizes well to both seen and unseen tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2605_30834
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
Park, Seongheon
Li, Wendi
Oh, Changdae
Yeh, Samuel
Kira, Zsolt
Hagenow, Michael
Li, Sharon
Robotics
Artificial Intelligence
Vision-Language-Action (VLA) models enable robots to follow natural language instructions and generalize across diverse tasks, but they remain vulnerable to execution failures that compromise reliability in real-world deployment. Detecting such failures during execution is therefore critical for the robust deployment of embodied systems. Existing failure detection methods either rely on expensive action resampling or external models, while alternatives propagate trajectory-level labels uniformly across every timestep, obscuring localized failure signals. In this paper, we propose \textbf{Hide-and-Seek}, a framework that formulates VLA failure detection as a coarsely supervised learning problem. By combining inter-trajectory and intra-trajectory contrastive objectives, Hide-and-Seek localizes failure-indicative actions and induces temporally structured failure signals from trajectory-level supervision alone, without any step-level annotation. We evaluate Hide-and-Seek on LIBERO, VLABench, and a real-world robotic platform across three representative VLA policies: OpenVLA, $π_0$, and $π_{0.5}$.Our method achieves state-of-the-art multi-task failure detection performance with a practical accuracy--timeliness trade-off under conformal prediction, and generalizes well to both seen and unseen tasks.
title Hide-and-Seek in Trajectories: Discovering Failure Signals for VLA Runtime Monitoring
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2605.30834