---
id: 20260820-T0-05
title: "Agentic AI安全新框架：运行时行为边界控制与可信溯源"
title_en: "Runtime governance framework for agentic AI: action-boundary control with trusted provenance"
url: https://ai.daily.yangsir.net/daily/20260820-T0-05
issue_date: 2026-08-20
publish_date: 2026-08-19T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2608.16891
---

# Agentic AI安全新框架：运行时行为边界控制与可信溯源

arXiv新论文提出Agentic AI的运行时治理方案，通过行为边界控制、可信溯源和失败闭环执行，解决工具调用带来的操作副作用安全问题。该框架超越纯文本提示词层面的治理，为文件修改、消息发送等高风险操作提供约束。

## English Version

**Runtime governance framework for agentic AI: action-boundary control with trusted provenance**

A new arXiv paper introduces a runtime governance framework for agentic AI, using action-boundary control, trusted provenance, and fail-closed execution to address safety issues from tool-use side effects. It goes beyond prompt-level governance to constrain file modifications, message sending, and other high-risk operations.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2608.16891)

**详情页**：https://ai.daily.yangsir.net/daily/20260820-T0-05

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*