论文研究 arXiv cs.AI Tue, 18 Aug 2026 正文 thin 4 words

Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement

英文标题:Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcement

arXiv:2608.14590v1 Announce Type: new Abstract: LLM agents increasingly perform irreversible real-world actions, including database updates, API calls, file operations, and autonomous use of tools. However, no existing system provides formally grounded, task-level safety guarantees for the plans th
打开原文相关 4.8 · 机会 4
media2.1 KB media640 B media612 B media380 B media9.1 KB media32.7 KB media22.8 KB media24.2 KB media34.7 KB

中文

arXiv:2608.14590v1 Announce Type: new Abstract: LLM agents increasingly perform irreversible real-world actions, including database updates, API calls, file operations, and autonomous use of tools. However, no existing system provides formally grounded, task-level safety guarantees for the plans th

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

×