ICAT: Incident-Case-Grounded Adaptive Testing for Physical-Risk Prediction in Embodied World Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917417316253696 |
|---|---|
| author | Lai, Zhenglin Huang, Sirui Li, Yuteng Huang, Changxin Li, Jianqiang Wu, Bingzhe |
| author_facet | Lai, Zhenglin Huang, Sirui Li, Yuteng Huang, Changxin Li, Jianqiang Wu, Bingzhe |
| contents | Video-generative world models are increasingly used as neural simulators for embodied planning and policy learning, yet their ability to predict physical risk and severe consequences is rarely evaluated.We find that these models often downplay or omit key danger cues and severe outcomes for hazardous actions, which can induce unsafe preferences during planning and training on imagined rollouts. We propose ICAT, which grounds testing in real incident reports and safety manuals by building structured risk memories and retrieving/composing them to constrain the generation of risk cases with causal chains and severity labels. Experiments on an ICAT-based benchmark show that mainstream world models frequently miss mechanisms and triggering conditions and miscalibrate severity, falling short of the reliability required for safety-critical embodied deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_16405 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ICAT: Incident-Case-Grounded Adaptive Testing for Physical-Risk Prediction in Embodied World Models Lai, Zhenglin Huang, Sirui Li, Yuteng Huang, Changxin Li, Jianqiang Wu, Bingzhe Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Video-generative world models are increasingly used as neural simulators for embodied planning and policy learning, yet their ability to predict physical risk and severe consequences is rarely evaluated.We find that these models often downplay or omit key danger cues and severe outcomes for hazardous actions, which can induce unsafe preferences during planning and training on imagined rollouts. We propose ICAT, which grounds testing in real incident reports and safety manuals by building structured risk memories and retrieving/composing them to constrain the generation of risk cases with causal chains and severity labels. Experiments on an ICAT-based benchmark show that mainstream world models frequently miss mechanisms and triggering conditions and miscalibrate severity, falling short of the reliability required for safety-critical embodied deployment. |
| title | ICAT: Incident-Case-Grounded Adaptive Testing for Physical-Risk Prediction in Embodied World Models |
| topic | Robotics Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2604.16405 |