# Beyond Behaviour: A Stimulus-Response Safety Evaluation of Vision-Language-Action Models

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.

## Why It Matters

This work touches on AI safety and trust: how models and agents are adversarially tested, aligned to reliable behavior, or audited for failure modes.

## Sources

- arXiv: [https://arxiv.org/abs/2610.34837](https://arxiv.org/abs/2610.34837)

*Back to [Recent News](../../news.md) · [Sub-article index](../index.md).*