{
  "id": 4193,
  "url": "https://arxiv.org/abs/2605.23989v1",
  "title": "Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security",
  "summary": "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 introduce new failure modes that challenge trustworthiness. This survey provides a focused examination of trustworthy agentic AI through two core dimensions that are critical for high-risk deployments: Safety and Robustness, and Privacy and System Security. For each dimension, we clarify key concep",
  "authors": "Jinhu Qi, Muzhi Li, Jiahong Liu, Yuqin Shu, Dianzhi Yu, Shicheng Ma et al.",
  "category": "research",
  "topics": "privacy-surveillance,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-17T10:26:37.000Z",
  "fetched_at": "2026-07-14T16:30:50.571Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4193",
  "original_url": "https://arxiv.org/abs/2605.23989v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}