---
id: 20260414-T0-03
title: "OpenKedge：通过执行边界安全和证据链治理AI代理突变"
title_en: "OpenKedge: Governing AI Agent Mutation with Execution-Bound Safety"
url: https://ai.daily.yangsir.net/daily/20260414-T0-03
issue_date: 2026-04-14
publish_date: 2026-04-13T04:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2604.08601
---

# OpenKedge：通过执行边界安全和证据链治理AI代理突变

研究者提出OpenKedge协议，解决当前API中心化架构的根本缺陷：概率系统直接执行状态变更但缺乏足够的上下文、协调或安全保证。该协议通过执行边界安全和证据链机制，为自主AI代理提供更可靠的状态变更控制框架，论文已发布于arXiv:2604.08601v1。

## English Version

**OpenKedge: Governing AI Agent Mutation with Execution-Bound Safety**

Researchers introduce OpenKedge, a protocol addressing fundamental flaws in API-centric architectures where probabilistic systems execute state mutations without sufficient safety. It provides execution-bound safety and evidence chains for reliable AI agent state control (arXiv:2604.08601v1).

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2604.08601)

**详情页**：https://ai.daily.yangsir.net/daily/20260414-T0-03

---

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