Investing in multi-agent AI safety research

投资多智能体 AI 安全研究

June 11, 2026 | Responsibility & Safety 2026 年 6 月 11 日 | 责任与安全

Google DeepMind, Schmidt Sciences, the Cooperative AI Foundation, ARIA and Google.org Share: Scaling AI Safety Research for a Multi-Agent World Google DeepMind、Schmidt Sciences、Cooperative AI Foundation、ARIA 和 Google.org 联合发布：为多智能体世界扩展 AI 安全研究

For the past decade, we’ve focused on making individual AI models more capable, helpful and safe. Today, Google DeepMind — together with Schmidt Sciences, the Cooperative AI Foundation, the Advanced Research and Invention Agency, and supported by Google.org — is announcing a new technical research funding call of up to $10M for researchers worldwide. 在过去的十年里，我们一直致力于使单个 AI 模型变得更强大、更有用且更安全。今天，Google DeepMind 携手 Schmidt Sciences、Cooperative AI Foundation、英国高级研究与发明局（ARIA），并在 Google.org 的支持下，宣布一项面向全球研究人员、总额高达 1000 万美元的全新技术研究资助计划。

As AI technology scales, we’re entering a new era. Soon, millions of AI agents — built by different organizations — will interact across digital environments, communicating, negotiating and transacting with one another. 随着 AI 技术的扩展，我们正在进入一个新时代。不久之后，由不同组织构建的数百万个 AI 智能体将在数字环境中进行交互，相互沟通、协商并进行交易。

When these systems interact, they must do so safely and predictably. This shift creates a vital opportunity: we can strengthen the safety and stability of the entire AI ecosystem from the very beginning. 当这些系统进行交互时，必须确保其过程是安全且可预测的。这种转变创造了一个至关重要的机会：我们可以在整个 AI 生态系统构建之初，就加强其安全性和稳定性。

The funding call focuses on the study of how large-scale multi-agent AI systems behave as a group, and how we can provide frameworks to understand and mitigate against potential risks. By empowering researchers globally, we aim to solve the “invisible” safety risks that arise when independent systems interact across different networks. 此次资助计划重点研究大规模多智能体 AI 系统如何以群体形式运作，以及我们如何提供框架来理解并减轻潜在风险。通过赋能全球研究人员，我们的目标是解决当独立系统跨不同网络交互时所产生的“隐形”安全风险。

Why the agent ecosystem matters

为什么智能体生态系统至关重要

When large groups of AI agents interact, new collective behaviors and capabilities can emerge suddenly. Currently, we lack the tools to predict, measure and monitor these transitions. Most safety evaluations analyze models in isolation. However, as we and others have previously argued, interacting autonomous agents can produce complex, “emergent” behaviors that are difficult to anticipate. 当大量 AI 智能体进行交互时，新的集体行为和能力可能会突然涌现。目前，我们缺乏预测、衡量和监控这些转变的工具。大多数安全评估都是在孤立状态下分析模型的。然而，正如我们和其他人之前所论证的那样，交互的自主智能体可能会产生难以预料的复杂“涌现”行为。

Because this is a new area of research, it is critical to understand how these shifts occur. For example, could they cause an unpredictable flurry of economic activity or lead to new security challenges? Understanding how to manage these system-wide behaviors is our core objective. 由于这是一个新的研究领域，理解这些转变如何发生至关重要。例如，它们是否会导致不可预测的经济活动激增，或引发新的安全挑战？理解如何管理这些系统范围内的行为是我们的核心目标。

Scaling the frontier of multi-agent safety research

扩展多智能体安全研究的前沿

Although foundational frameworks for multi-agent safety exist, the rapid evolution of these systems requires an immediate, large-scale expansion of research. 尽管目前已存在多智能体安全的基础框架，但这些系统的快速演进要求我们立即进行大规模的研究扩展。

Our 2025 research established a framework for understanding these interactions, while our recent work on AI Agent Traps explores vulnerabilities agents face in adversarial environments. Now, we must move faster. We are at a critical juncture where the complexity of multi-agent interactions is outpacing existing safety models. 我们 2025 年的研究建立了一个理解这些交互的框架，而我们最近关于“AI 智能体陷阱”（AI Agent Traps）的工作则探讨了智能体在对抗性环境中面临的漏洞。现在，我们必须加快步伐。我们正处于一个关键时刻，多智能体交互的复杂性正在超过现有的安全模型。

This funding call aims to accelerate progress by supporting a global network of independent researchers. A diverse community is essential to ensure safety standards are transparent and robust for everyone. 此次资助计划旨在通过支持全球独立研究人员网络来加速进展。一个多元化的社区对于确保安全标准对所有人而言都是透明且稳健的至关重要。

This effort also advances the mission of Schmidt Sciences’ Science of Trustworthy AI and AI Agents programs, which support foundational work on understanding and mitigating risks from frontier AI systems, as well as ARIA’s Scaling Trust programme, which seeks to unlock new forms of cyber-physical multi-agent coordination. 这项工作也推进了 Schmidt Sciences 的“可信 AI 与 AI 智能体科学”项目的使命，该项目支持理解和减轻前沿 AI 系统风险的基础性工作；同时也推进了 ARIA 的“扩展信任”（Scaling Trust）计划，该计划旨在解锁新型的网络物理多智能体协作。

A collaborative call to action

协作行动号召

No single lab can solve multi-agent safety alone. We invite academic and independent researchers to submit proposals in four priority areas: 没有任何一个实验室可以独自解决多智能体安全问题。我们邀请学术界和独立研究人员在以下四个优先领域提交提案：

• Sandboxes and testbeds: Building realistic, reproducible environments to evaluate, compare and accelerate progress across all areas of multi-agent safety. This includes virtual marketplaces, simulated ecosystems and multi-organisation workflows. 沙盒与测试平台： 构建真实、可复现的环境，以评估、比较并加速多智能体安全各领域的进展。这包括虚拟市场、模拟生态系统和多组织工作流。
• The science of agent networks: Understanding the safety-relevant properties of interacting agent populations, including investigating how collective capabilities emerge and scale, how networks fail or become volatile and how to detect dangerous, unexpected population-level properties. 智能体网络科学： 理解交互智能体群体的安全相关属性，包括研究集体能力如何涌现和扩展，网络如何失效或变得不稳定，以及如何检测危险的、意料之外的群体级属性。
• Strengthening agent infrastructure: Stress-testing the protocols for identity, reputation and commitment that are secure cross-platform agent interactions. 加强智能体基础设施： 对确保跨平台智能体交互安全的身份、声誉和承诺协议进行压力测试。
• Oversight and control: Developing methods to monitor deployed agent populations and mitigate collective harms at scale. 监督与控制： 开发监控已部署智能体群体并大规模减轻集体危害的方法。

How to participate

如何参与

We invite researchers to review our call for proposals and join us in building a safe foundation for a multi-agent future. 我们邀请研究人员查阅我们的提案征集书，并加入我们，共同为多智能体的未来构建安全基础。

The deadline to apply is August 8, 2026, with awardees expected to be announced in Autumn 2026. 申请截止日期为 2026 年 8 月 8 日，获奖者预计将于 2026 年秋季公布。

For more details on technical requirements and the application process, visit our application portal. 有关技术要求和申请流程的更多详细信息，请访问我们的申请门户网站。