AI RESEARCH
Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security
arXiv CS.AI
•
ArXi:2605.23989v1 Announce Type: new Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories