1
Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security
36页全面综述，系统梳理agentic AI在安全、鲁棒性、隐私和系统安全四大维度的挑战与进展，构建可信AI框架。
arXiv:2605.23989v1 Announce Type: new Abstract: Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long…