The paper proposes a scalable trust discovery architecture for the Internet of Agents (IoA), addressing unresolved issues of agent registration, trust identification, and capability discovery across heterogeneous platforms. The architecture is hierarchical and distributed, consisting of three layers: Agent Root, Agent Registry, and Agent Resolver. It introduces a registry-suffix-anchored composite identity scheme and a dual-certificate multi-level authentication mechanism to strengthen identity trust.
The authors implemented a prototype and evaluated it with large-scale experiments. The prototype achieved an average registration latency of 58ms and an average discovery latency of 25ms. It supports over 19,000 registration requests per second and over 29,000 agent discovery requests per second.
These results demonstrate the feasibility of the proposed architecture for scalable and identity-trusted agent ecosystems. The approach provides a practical way to enable trustworthy collaboration among autonomous agents in the IoA.