AI-1143 - USA (New York) - Scaling AI Safety Service for a Multi-Agent World - Deadline August 9,2026

(1) Vendor needs to provide scaling AI safety service for a multi–agent world. • Scalable to a realistic number of agents and an appropriate diversity of agentic tools, knowledge bases, etc.;• High–fidelity, capturing behaviours of frontier AI agents rather than coarse abstractions;• Externally valid, enabling a principled characterisation of the deployment conditions under which simulation–derived conclusions should and should not be trusted;• Safe and secure, allowing dangerous collective behaviours to be studied without risk of uncontrolled deployment;• Reproducible, enabling researchers to compare different methods.• Developing principled methods to utilise data from real–world deployments to design grounded environments and to evaluate their external validity;• Evaluating vulnerabilities in networks of AI agents. • New evaluation frameworks for risks specific to multi–agent deployments, such as resilience to adversarial sub–populations, propagation of attacks between agents and susceptibility to cascading failures.