arXiv cs.AI· Vy Vo, Dinh Phung·· 14 小时前AI 评分38
超越行为：视觉-语言-动作模型的安全刺激-反应评估
Beyond Behaviour: A Stimulus-Response Safety Evaluation of Vision-Language-Action Models
AI 导读
研究在三个模型和两个视频基准上考察视觉-语言-动作模型面对可见危险与有害后果时的内部表征和动作倾向，发现即使危险在模型内部已被识别，执行任务仍可能是默认反应。
正文 · 原文
Abstract:Humans exhibit biological sensitivity to safety-critical stimuli that can trigger defensive action. Across three models and two video benchmarks, we investigate whether similar responses emerge in vision-language-action models by examining their internal representations and action tendencies in response to visible hazards and harmful consequences. Our findings suggest that task execution may remain the default response even when danger is internally registered.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.34837 [cs.AI] |
| (or arXiv:2610.34837v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.34837 arXiv-issued DOI via DataCite (pending registration) |
|
| Journal reference: | The Science of Physical AI Safety workshop at CoRL 2026 |
Submission history
From: Vy Vo [view email]
[v1]
Mon, 26 Oct 2026 04:36:21 UTC (4,199 KB)
来源：arXiv cs.AI · arxiv.org