Cisco 的 Outshift 部门正在为多代理 AI 系统开发一种新架构，旨在使它们能够协作并解决超出单个代理范围的复杂问题。这种被称为“认知互联网”的方法依赖于一个基础的“代理互联网”层来进行发现和通信。目标是通过允许代理共享意图、上下文和推理来创建分布式超级智能，从而模仿人类文明的演变。 AI
影响 这种架构转变有可能使 AI 系统能够解决更复杂的问题，超越单个代理的能力。
排序理由 该条目描述了一种用于多代理系统的新架构方法和项目，而不是前沿模型发布或行业范围内的重大事件。
AI 生成摘要 · Google Gemini · 来自 3 个来源。 我们如何撰写摘要 →
完整方法见我们的编辑标准。
<p><span>It’s an old story. An immortal lives long enough that at some point, whether by folly or design, they invent their own death. Infinity – the fact that given enough time every possible happening will happen – isn’t the most interesting part of these tales. No, it’s the su…
Imagine a healthcare system made up of multiple AI agents: one that manages symptom assessment, another scheduling, a third insurance, and a fourth pharmacy. Each is an expert in its domain. But they all have their own distinct knowledge and objectives. Today they can exchange da…
https://www. deutschlandfunk.de/superintell igenz-wie-gefaehrlich-ist-die-ki-der-zukunft-100.html # KI # AI # Risiko # risk # DLF