# Do Frontier Models Seek Safety Evidence Before Acting?

> 标题为英语

> 全文为英语

**Published:** 2026年9月17日
**Author:** Omer Tafveez
**Source:** arXiv — cs.AI
**Language:** en-US
**HTML:** https://aiqazaqstan.com/zh/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…

> 内容来自原始来源： **arXiv — cs.AI**
> [在 arXiv — cs.AI 阅读全文](https://arxiv.org/abs/2609.17865)

**标签：** #Anthropic #arXiv #Claude 3.5

---

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