**The Provenance Tax: How LLM Watermarking Changes AI Agent Behavior** > Lasso

**The Provenance Tax: How LLM Watermarking Changes AI Agent Behavior**

> Lasso Research tested SynthID-Text watermarking across six models and found it changes tool-call correctness and weakens refusal under prompt injection. On some models, watermark-induced behavioral churn exceeds what a temperature change produces. Back to research The Provenance Tax: Understanding the Impact of LLM Watermarking on AI Agent Behavior Andrea Siposova September 17, 2026 4 min read On this page This is a...

**来源信息**
- **来源**：Hacker News：AI 热帖
- **分类**：论文
- **发布时间**：2026-09-18 11:53（北京时间）
- **原文**：[打开原文](https://www.lasso.security/blog/the-provenance-tax-understanding-the-impact-of-llm-watermarking-on-ai-agent-behavior)