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
From the original article
1 min read at arxiv.orgThe 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.
By Song Zhang · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.