# Do Frontier Models Seek Safety Evidence Before Acting?

**Published:** September 17, 2026
**Author:** Omer Tafveez
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/en/articles/do-frontier-models-seek-safety-evidence-before-acting

Frontier models are often evaluated on how they respond to safety information once it is already in context. We study an earlier decision point: whether models choose to acquire safety-relevant evidence before acting. We introduce SAFE, a controlled benchmark in which models…

> From the original source: **arXiv — cs.AI**
> [Read full article at arXiv — cs.AI](https://arxiv.org/abs/2609.17865)

**Tags:** #Anthropic #arXiv #Claude 3.5

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*