1
ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents
首个专注LLM代理工具使用中「目的绑定」隐私的基准测试框架，揭示AI隐私保护新维度。
arXiv:2606.28061v1 Announce Type: cross Abstract: Large language models (LLMs) have increasingly moved from standalone text generation systems to agen…