Operational Hallucination and Safety Drift in AI Agents
英文标题：Operational Hallucination and Safety Drift in AI Agents
arXiv:2607.18366v1 Announce Type: new Abstract: Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution. While single-turn safety mechanisms are relatively mature, extended interactions reveal structural vulnerabil
打开原文相关 3.2 · 机会 2
2.1 KB
612 B
380 B
9.1 KB
32.7 KB
22.8 KB
24.2 KB
34.7 KB
中文
arXiv:2607.18366v1 Announce Type: new Abstract: Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution. While single-turn safety mechanisms are relatively mature, extended interactions reveal structural vulnerabil
中文全文翻译正在补齐，可先查看下方英文原文。
English / 原文
BibTeX formatted citation
×