The path to artificial superintelligence

通往人工超级智能之路

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 data, but they are not yet able to actually coordinate patient care without a human making the decisions. 想象一个由多个 AI 智能体组成的医疗保健系统：一个负责症状评估，一个负责预约排程，一个负责保险，还有一个负责药房。每个智能体都是其领域内的专家，但它们各自拥有独特的知识和目标。如今，它们虽然可以交换数据，但在没有人类决策的情况下，还无法真正协调患者的护理工作。

“The intelligence is already there. What is missing is the connective tissue that turns four strangers into one team,” explains Vijoy Pandey, senior vice president and general manager of Outshift by Cisco. This “connective tissue” comes from adding a semantic layer—what Outshift calls the “Internet of Cognition”—that enables agents across domains to work together and, critically, “think” together through shared intent, context, and reasoning. “智能已经具备了，缺失的是将四个‘陌生人’变成一个团队的‘结缔组织’，”思科 Outshift 高级副总裁兼总经理 Vijoy Pandey 解释道。这种“结缔组织”源于增加一个语义层——Outshift 将其称为“认知互联网”（Internet of Cognition）——它使跨领域的智能体能够协同工作，更关键的是，通过共享意图、上下文和推理来共同“思考”。

This semantic layer relies on a connectivity layer beneath it called the “Internet of Agents,” which allows autonomous agents to discover one another, prove identity, and exchange messages across domains. When used together, they enable “the next step on the road to distributed artificial superintelligence,” says Pandey. 这一语义层依赖于其下方的连接层，即“智能体互联网”（Internet of Agents），它允许自主智能体在跨领域中相互发现、验证身份并交换信息。Pandey 表示，当两者结合使用时，它们就实现了“通往分布式人工超级智能之路的下一步”。

From solo silicon savants to the ‘Internet of Cognition’

从单打独斗的硅基天才到“认知互联网”

For years, the AI industry has been focused on growth. Scaling vertically has led to bigger models, trained on more data with more compute. This has produced the reasoning capabilities that can be like a “brain” for AI agents, which can perceive, reason, and act in digital environments. While vertical scaling can produce more capable agents perpetually, to enable agentic problem solving across different systems, companies, and platforms the next axis of scale must be horizontal, says Pandey. 多年来，AI 行业一直专注于增长。垂直扩展带来了更大的模型，这些模型通过更多的数据和算力进行训练。这产生了类似于 AI 智能体“大脑”的推理能力，使其能够在数字环境中感知、推理和行动。Pandey 指出，虽然垂直扩展可以不断产生能力更强的智能体，但要实现跨不同系统、公司和平台的智能体问题解决能力，下一个扩展维度必须是水平扩展。

Multi-agent systems are already being explored in areas like software engineering, drug discovery, and scientific simulations, but their performances so far have been underwhelming. One study finds a failure rate of between 41% and around 87% when evaluating seven open-source multi-agent systems. “Connected agents handle coordinated action well; taking a task whose shape they have seen, divided and passed around,” Pandey explains. “What they cannot do is hold a goal in common and reason toward something none of them was trained to solve.” 多智能体系统已经在软件工程、药物发现和科学模拟等领域得到探索，但迄今为止它们的表现并不理想。一项研究发现，在评估七个开源多智能体系统时，失败率在 41% 到 87% 之间。“连接起来的智能体可以很好地处理协调行动；它们能处理自己熟悉形状的任务，进行拆分并传递，”Pandey 解释道。“但它们无法做到的是共同持有一个目标，并针对它们从未受过训练的问题进行推理。”

“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.” “这种差距是架构上的，而不是提示词（prompting）的问题，”Pandey 补充道。“如果没有合适的协调层，简单的多智能体设置表现甚至可能不如单个智能体。真正的跨越式变化在于，智能体团队能够自行针对新问题达成共识，而无需人类在中间进行缝合。”

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). 为了实现这一目标，Pandey 表示 Outshift 构建了一个名为 AGNTCY 的连接层，这是一个目前隶属于 Linux 基金会的开源项目。AGNTCY 允许跨不同系统、公司和平台的智能体通过开放的标准化协议相互发现、验证身份并交换信息。正如 Pandey 所解释的那样，这使得“认知互联网”的理论更进一步。它创建了一个语义层，允许智能体对齐目标（共享意图）、汇集机构知识并复合记忆（共享上下文），以及进行集体权衡（共享推理）。

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. Pandey 将这一进程比作人类的发展：“几十万年来，人类个体变得越来越聪明，但这些进步随着每个人的离世而消失，”他解释道。“大约 7 万年前，情况发生了变化，人类学会了共享意图、积累知识并集体推理。那时，分散的个体才成为了文明。智能体正处于同样的门槛上。我们已经创造了硅基天才并赋予了它们代理权。它们所缺乏的，正是让人类走向集体化的那一层。”

First steps to distributed superintelligence

通往分布式超级智能的第一步

Enabling agents to work collectively rests on three pillars in the tech stack: 使智能体能够集体工作，依赖于技术栈中的三大支柱：

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. “A coordination protocol that makes agents declare a goal, surface missing information, and resolve conflicts before acting raised that to 93%.” 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，允许智能体在行动前就目标达成一致，并在过程中进行协商。Outshift 创建了一个名为 Mycelium 的开源协调层，组织可以克隆并将其应用于自己的智能体。“我们发现，在 14 种场景下，非结构化的智能体群体只有约三分之一的时间能达成决策，”Pandey 说。“而使用一种要求智能体在行动前声明目标、提出缺失信息并解决冲突的协调协议，这一成功率提高到了 93%。”
Shared context through cognition fabric: A cognition fabric is a shared institutional memory and communication mesh that allows agent insight to compound over time rather than resetting each session. This policy-governed context layer solves the problem of “organizational amnesia,” says Pandey, by ensuring the baseline intelligence of the systems only ever goes up. 通过认知结构（Cognition Fabric）共享上下文： 认知结构是一种共享的机构记忆和通信网格，它允许智能体的洞察力随时间积累，而不是在每次会话后重置。Pandey 表示，这种由策略管理的上下文层通过确保系统的基准智能水平只升不降，解决了“组织性失忆”的问题。
Shared reasoning through cognitive amplifiers and guardrail technologies: Two kinds of cognition engine can be used together to enable shared reasoning. Cognitive amplifiers speed up shared reasoning and modeling, and guardrail technologies (GATs) create security, cost, and compliance frameworks. Humans are active contributors to this layer, making judgment calls the system routes to them (rather than reviewing outputs after the fact). 通过认知放大器和护栏技术共享推理： 两种认知引擎可以结合使用以实现共享推理。认知放大器加速共享推理和建模，而护栏技术（GATs）则创建安全、成本和合规框架。人类是这一层的积极贡献者，负责做出系统路由给他们的判断决策（而不是事后审查输出结果）。

Cognition sharing in multi-agent systems can create new risks, including unintended delegations, malicious prompt injections or memory poisoning, or over-privileged agents with access to permissions and data far beyond what their tasks require. Environment-specific controls are therefore needed to protect against unintended actions or consequences. “Agents have human-like attributes but operate at machine speed and scale,” says Pandey. “Everything we built for twenty years—access control, identity, compliance—was built for humans or machines, not both.” Continuous Agent Semantic Authorization (CASA)—an open-source reference implementation developed by Outshift—is a GAT that works to ensure agent actions remain securely aligned with… 多智能体系统中的认知共享可能会带来新的风险，包括意外的授权、恶意的提示词注入或记忆投毒，以及拥有超出任务所需权限和数据的过度授权智能体。因此，需要针对特定环境的控制措施来防止意外行为或后果。“智能体具有类似人类的属性，但以机器的速度和规模运行，”Pandey 说。“我们过去二十年构建的一切——访问控制、身份验证、合规性——都是为人类或机器单独设计的，而不是两者兼顾。”由 Outshift 开发的开源参考实现——持续智能体语义授权（CASA）——就是一种旨在确保智能体行为始终安全地与……保持一致的护栏技术。