Upgrade or Switch: Do We Need a New Registry Architecture for the Internet of AI Agents?

2025-06-13

AI Summary

The emergence of AI agent internet introduces unprecedented requirements for millisecond-scale service discovery, instantaneous credential revocation, and cryptographically verifiable behavioral integrity—fundamental qualitative shifts exceeding the capabilities of existing infrastructure (e.g., DNS, PKI). Method: We systematically compare three architectural approaches—incremental upgrades to legacy systems, full-stack replacement, and hybrid registration—and propose a “centralized registration + federated mesh” paradigm: critical agents are registered via trusted central authorities, while domain-specific scenarios leverage decentralized identifiers (DIDs) and low-latency service discovery for autonomous negotiation. Contribution/Results: Empirical evaluation using cryptographic behavioral proofs and DID-based authentication demonstrates that conventional DNS, IPv4/IPv6, and PKI cannot scale to trillion-agent deployments. The hybrid architecture achieves both near-term deployability and long-term evolvability, establishing an optimal, AI-native network registration framework.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent/AI Theories and Architectures
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Systems and Infrastructure for Web, Mobile and WoT: Decentralized Web and Fediverse systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The emerging Internet of AI Agents challenges existing web infrastructure designed for human-scale, reactive interactions. Unlike traditional web resources, autonomous AI agents initiate actions, maintain persistent state, spawn sub-agents, and negotiate directly with peers: demanding millisecond-level discovery, instant credential revocation, and cryptographic behavioral proofs that exceed current DNS/PKI capabilities. This paper analyzes whether to upgrade existing infrastructure or implement purpose-built registry architectures for autonomous agents. We identify critical failure points: DNS propagation (24-48 hours vs. required milliseconds), certificate revocation unable to scale to trillions of entities, and IPv4/IPv6 addressing inadequate for agent-scale routing. We evaluate three approaches: (1) Upgrade paths, (2) Switch options, (3) Hybrid registries. Drawing parallels to dialup-to-broadband transitions, we find that agent requirements constitute qualitative, and not incremental, changes. While upgrades offer compatibility and faster deployment, clean-slate solutions provide better performance but require longer for adoption. Our analysis suggests hybrid approaches will emerge, with centralized registries for critical agents and federated meshes for specialized use cases.

Problem

• Analyze upgrade vs. new registry for AI agent internet
• Address DNS, PKI limitations for autonomous agent needs
• Evaluate hybrid registries for scalable AI agent infrastructure

Innovation

• Analyze upgrade or switch for AI agent registries
• Evaluate DNS, PKI limitations for agent needs
• Propose hybrid centralized and federated registry solutions