AgentDNS: A Root Domain Naming System for LLM Agents
Enfang Cui, Yujun Cheng, Rui She, Dan Liu, Zhiyuan Liang, Minxin Guo, Tianzheng Li, Qian Wei, Wenjuan Xing, Zhijie Zhong
TL;DR
The paper tackles the challenge of cross-vendor service discovery, interoperability, and authentication for LLM agents. It introduces AgentDNS, a DNS-inspired root-domain naming and discovery system that supports semantic naming, natural-language service discovery, protocol-aware interoperability, and unified authentication and billing. The architecture comprises registration, search, resolution, proxy, billing, and authentication components, and a case study illustrates an end-to-end workflow from action-plan generation to secure service invocation. By decoupling agent identifiers from physical addresses and enabling real-time metadata resolution, AgentDNS facilitates autonomous, cross-organizational collaboration among heterogeneous agents and tools, with future work pointing to decentralization, privacy-preserving discovery, and planning-LLM integration.
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.