AgentDNS: A Root Domain Naming System for LLM Agents

2025-05-28

AI Summary

To address the lack of standardized protocols for cross-vendor and cross-organizational service discovery in the LLM agent ecosystem, this paper proposes the first DNS-inspired, semantics-aware service discovery system tailored for AI agents. The system comprises a distributed registry, a semantic routing engine, a zero-trust invocation gateway, and a unified billing protocol—enabling autonomous resolution, verifiable identity authentication, and cross-domain billing aggregation. Its core innovation lies in semantically adapting the DNS architecture to the LLM agent context, unifying service addressing, secure invocation, and financial settlement. Experimental evaluation in real-world deployments demonstrates significant improvements: +23.6% in service discovery accuracy and +19.4% in invocation success rate. The implementation is open-sourced.

Technology Category

• Multiagent Systems: Agent Communication
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

The rapid evolution of Large Language Model (LLM) agents has highlighted critical challenges in cross-vendor service discovery, interoperability, and communication. Existing protocols like model context protocol and agent-to-agent protocol have made significant strides in standardizing interoperability between agents and tools, as well as communication among multi-agents. However, there remains a lack of standardized protocols and solutions for service discovery across different agent and tool vendors. In this paper, we propose AgentDNS, a root domain naming and service discovery system designed to enable LLM agents to autonomously discover, resolve, and securely invoke third-party agent and tool services across organizational and technological boundaries. Inspired by the principles of the traditional DNS, AgentDNS introduces a structured mechanism for service registration, semantic service discovery, secure invocation, and unified billing. We detail the architecture, core functionalities, and use cases of AgentDNS, demonstrating its potential to streamline multi-agent collaboration in real-world scenarios. The source code will be published on https://github.com/agentdns.

Problem

• Standardizing service discovery for cross-vendor LLM agents
• Enabling secure invocation of third-party agent services
• Facilitating interoperability across organizational and technological boundaries

Innovation

• Root domain naming for LLM agents
• Semantic service discovery mechanism
• Secure cross-vendor service invocation