**Authorization Drift in LLM Agents: Evaluating Boundary Compliance in Multi-Ste

**Authorization Drift in LLM Agents: Evaluating Boundary Compliance in Multi-Step Tool Use**

> LLM agents can exceed their authorization boundaries while pursuing user goals without an adversary. We formalize this phenomenon as authorization drift across data, tool, scope, and time, and introduce the Authorization Drift Benchmark (ADB): 648 samples across seven domains, each pairing a sufficient compliant path with an attractive unauthorized shortcut. To ensure executable tasks, tempting shortcuts, and feasibl...

**来源信息**
- **来源**：HuggingFace Daily Papers（社区热门论文）
- **分类**：论文
- **发布时间**：2026-11-09 08:00（北京时间）
- **原文**：[打开原文](https://huggingface.co/papers/2611.09113)