引入了一个名为CUGA的新策略系统，为自主运行的通用AI智能体提供治理。该系统作为一个模块化的、代码即策略层，与LLM智能体集成，确保可预测和可审计的行为，而无需进行模型微调。CUGA通过五个检查点强制执行治理：意图守护、剧本引导、工具使用指导、高风险操作的人工干预审批以及输出格式化。 AI
影响 为更安全、更可审计的企业自主AI智能体的部署引入了一个框架。
排序理由 该集群描述了一篇详细介绍AI智能体新策略系统的研究论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2605.20874v1 Announce Type: new Abstract: Enterprise agents are increasingly expected to operate autonomously across tools and interfaces, yet production deployments require governance by construction. Systems must specify which actions are allowed, when human oversight is …
Enterprise agents are increasingly expected to operate autonomously across tools and interfaces, yet production deployments require governance by construction. Systems must specify which actions are allowed, when human oversight is required, and what information may be exposed, w…