通往人工超级智能之路

英文标题：The path to artificial superintelligence

Outshift 认为，多智能体系统的关键瓶颈在于架构与协调层，而非单纯改进提示词。其开源项目 AGNTCY 旨在让跨系统、跨公司和跨平台的 Agent 能够发现彼此、验证身份，并通过开放标准协议交换信息。该公司还提出以认知状态协议共享意图，并称内部测试显示，引入协调协议后，Agent 团队在 14 个场景中的决策达成率从约三分之一提升至 93%。这类协调能力被视为推动 Agent 从独立工作走向集体推理、并迈向分布式超级智能的重要基础设施。

打开原文相关 3 · 机会 1

中文

“差距在于架构，而不是提示词问题，”Pandey 补充道。“如果没有合适的协调层，朴素的多智能体配置可能比单个 Agent 的表现更差。真正的跃迁，是一支 Agent 团队能够在一个新问题上自行达成一致，而无需人类去缝合其中的衔接。”

为了实现这一目标，Pandey 表示，Outshift 构建了一个名为 AGNTCY 的连接层。AGNTCY 是一个现已归入 Linux Foundation 的开源项目。它使不同系统、公司和平台中的 Agent 能够相互发现、证明身份，并通过开放、标准化的协议交换消息。

正如 Pandey 所解释的，这让“认知互联网”（Internet of Cognition）的论点得以更进一步。它创建了一个语义层，使 Agent 能够对齐目标（共享意图）、汇集机构知识并累积记忆（共享上下文），以及进行集体权衡（共享推理）。

Pandey 将这一演进类比为人类的发展：“数十万年来，人类个体变得越来越聪明，但这些进步会随着取得它们的人离世而消失，”他解释道。“大约 7 万年前，这种情况发生了改变：人类学会了共享意图、建立累积性知识，并进行集体推理。也正是在那时，分散的个体变成了文明。

“Agent 正处于同样的临界点。我们已经构建出硅基天才，并赋予它们自主性。它们所缺少的，是让人类能够走向集体协作的那一层，”他说。

迈向分布式超级智能的第一步

让 Agent 能够集体协作，依赖于技术栈中的三大支柱：

**通过认知状态协议共享意图：**认知状态协议是一种语义握手机制，使 Agent 能够在行动前就目标达成共识，并随后围绕该目标进行协商。Outshift 创建了一个名为 Mycelium 的开源协调层，组织可以将其克隆并用于自身的 Agent。

“在 14 个场景中，我们发现非结构化群体大约只有三分之一的时间能够达成决策，”Pandey 在谈及内部测试时表示。“一种让 Agent 在行动前声明目标、暴露缺失信息并解决冲突的协调协议，将这一比例提高到了 93%。”

English / 原文

“The gap is architectural, not a prompting problem,” Pandey adds. “Without the right coordination layer, naive multi-agent setups can perform worse than a single agent. The step change is that team of agents converging on its own, on a new problem, with no human stitching the seams.”

To reach this goal, Pandey says Outshift has built a connectivity layer called AGNTCY, an open-source project now under the Linux Foundation. AGNTCY allows agents across different systems, companies, and platforms to find each other, prove identity, and exchange messages through open, standardized protocols.

And, as Pandey explains, this allows the Internet of Cognition thesis to take a step further. It creates a semantic layer that allows agents to align goals (share intent), pool institutional knowledge and compound memory (share context), and make collective trade-offs (share reasoning).

Pandey likens this progression to that of humans: “For hundreds of thousands of years humans got individually smarter, and the gains died with each person who made them,” he explains. “Around 70,000 years ago that changed, when humans learned to share intent, build cumulative knowledge, and reason collectively. That is when scattered individuals became civilization.

“Agents are at the same threshold. We have built the silicon geniuses and given them agency. What they lack is the layer that let humans go collective,” he says.

First steps to distributed superintelligence

Enabling agents to work collectively rests on three pillars in the tech stack:

Shared intent through cognition state protocols: Cognition state protocols are the semantic handshake that allow agents to agree on a goal before they act and then negotiate toward it. Outshift has created an open-source coordination layer called Mycelium, which organizations can clone and use against their own agents.

“We found that unstructured groups reached a decision about a third of the time across 14 scenarios,” says Pandey, speaking about internal testing. “A coordination protocol that makes agents declare a goal, surface missing information, and resolve conflicts before acting raised that to 93%.”