Abstract

The emerging Internet of Agents—a global environment in which LLM-powered agents discover peers, negotiate trust, invoke tools, and delegate tasks across organizational boundaries—is currently being standardized from the communication layer upward. Protocols increasingly specify how agents exchange messages, but not how an agent proves what it is, what it is authorized to do, whether its advertised capabilities are genuine, or how its actions remain accountable after delegation. We argue that this leaves the ecosystem without the foundation for secure interoperability. We present InterSAGE, a trust-native protocol suite that supplies this trust substrate alongside existing Internet and agent communication protocols.