A Scalable Trust Discovery Architecture for the Internet of Agents
Researchers propose a three-layer trust discovery architecture for the Internet of Agents with registry-anchored identities, sustaining 19,000 registrations and 29,000 discoveries per second.
Researchers propose a three-layer trust discovery architecture for the Internet of Agents: Agent Root for trusted registry governance, Agent Registry for agent registration and metadata publication, and Agent Resolver for distributed trust-aware capability discovery. It binds native agent identifiers to trusted registry suffixes for globally discoverable composite identities and uses dual certificates with multi-level authentication. A prototype sustains over 19,000 registration requests and 29,000 discovery requests per second with average latencies of 58ms and 25ms respectively.
- Three-layer design: Agent Root, Agent Registry, and Agent Resolver for distributed trust-aware discovery
- Registry-suffix-anchored composite identity binds native agent IDs to trusted registry suffixes
- Dual-certificate, multi-level authentication strengthens identity trust between agents
- Prototype handles 19,000+ registrations and 29,000+ discoveries per second at 58ms/25ms latency
Full article213 words · extracted from arxiv.org · click to collapse
The Internet of Agents is expected to enable large numbers of autonomous agents to discover, verify, and collaborate with each other across heterogeneous platforms. However, current agent protocols mainly address tool invocation and inter-agent communication, leaving scalable agent registration, trustworthy identification, and capability-oriented discovery largely unresolved. To address this, this paper proposes a scalable trust discovery architecture for the Internet of Agents. The proposed architecture adopts a hierarchical and distributed design consisting of three layers: Agent Root for trusted registry governance, Agent Registry for agent registration and metadata publication, and Agent Resolver for distributed capability discovery and trust-aware resolution. The architecture further introduces a registry-suffix-anchored composite identity scheme, which binds an agent native identifier to a trusted registry suffix to generate a globally discoverable identity. It also incorporates a dual-certificate and multi-level authentication mechanism to strengthen identity trust among agents. We implement a prototype and evaluate it through large-scale agent registration and resolution experiments. The prototype achieves an average registration latency of 58ms and an average discovery latency of 25ms, and it supports more than 19,000 registration requests per second and more than 29,000 agent discovery requests per second. These results demonstrate the feasibility of the proposed architecture, providing a practical approach toward scalable and identity-trusted agent ecosystems in the Internet of Agents.
Text extracted automatically; images, tables and formatting may be missing. Original: https://arxiv.org/abs/2609.20095