Scaling AI Safety Research for a Multi-Agent World
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, ARIA, and supported by Google.org, is announcing a new technical research funding call of up to $10M for researchers worldwide.
As AI technology scales, we’re entering a new era where millions of AI agents built by different organizations will interact across digital environments, communicating, negotiating, and transacting with one another. These systems must interact safely and predictably. This shift presents a vital opportunity to strengthen the safety and stability of the entire AI ecosystem from the very beginning.
The funding call focuses on studying how large-scale multi-agent AI systems behave as a group and how to provide frameworks to understand and mitigate potential risks. By empowering researchers globally, we aim to solve the “invisible” safety risks arising from independent systems interacting across different networks.
Why the Agent Ecosystem Matters
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 argued previously, interacting autonomous agents can produce complex, emergent behaviors that are difficult to anticipate. Understanding how to manage these system-wide behaviors is our core objective.
Scaling the Frontier of Multi-Agent Safety Research
Although foundational frameworks for multi-agent safety exist, the rapid evolution of these systems necessitates an immediate and large-scale expansion of research. 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. We must move faster, as the complexity of multi-agent interactions is outpacing existing safety models. This funding call aims to accelerate progress by supporting a global network of independent researchers.
A Collaborative Call to Action
No single lab can solve multi-agent safety alone. We invite academic and independent researchers to submit proposals in four priority areas:
- Sandboxes and testbeds: Building realistic, reproducible environments to evaluate, compare, and accelerate progress across multi-agent safety.
- The science of agent networks: Understanding safety-relevant properties of interacting agent populations, including how collective capabilities emerge and scale.
- Strengthening agent infrastructure: Stress-testing protocols for identity, reputation, and commitment to ensure secure cross-platform agent interactions.
- Oversight and control: Developing methods to monitor deployed agent populations and mitigate collective harms at scale.
We invite researchers to review our call for proposals and join us in building a safe foundation for a multi-agent future. The deadline to apply is August 8, 2026, with awardees expected to be announced in Autumn 2026. For more details on technical requirements and the application process, visit our application portal.
Blogger's Review: As AI rapidly evolves, the safety of multi-agent systems is a pressing issue. This funding call not only provides financial support to researchers but also fosters collaboration across various fields, aiming to effectively address potential security risks in the future. The complex interactions of multi-agents require new frameworks to ensure safety and reliability.