Discovering Agents for Discovery: The Case for DNS
2026-06-01 • Networking and Internet Architecture
Networking and Internet Architecture
AI summaryⓘ
The authors explain that as AI agents spread widely on the Internet, it will be hard for them to find and connect with each other. They suggest using the Domain Name System (DNS), which is already widely used for locating websites, to help AI agents discover one another reliably and quickly. They tested this idea using data from many real-world services and found that DNS can handle the needed information without slowing things down. Their work shows that DNS is a practical way to make AI agents easier to find and connect safely on a large scale.
Artificial Intelligence agentsDomain Name System (DNS)AI agent discoverymetadataauthenticationlatencyservice endpointsnetwork scalabilityauthorization
Authors
Ramachandra Rao Seethiraju, Sameer Thakar, Karthik Shyamsunder, Eric Osterweil
Abstract
As Artificial Intelligence (AI) agents enter their next stage of being deployed ubiquitously throughout the Internet, their discoverability will become a central challenge. The information AI agents need to discover one another, how they will locate it, how to facilitate authentication, integrity, and authorization, how to connect across different platforms, and how to scale across organizational boundaries form a set of unanswered challenges that deployment success will prompt. These are challenges for which one of the Internet's most venerable, solid, and ubiquitous infrastructures is ideally suited: The Domain Name System (DNS). Such a rich, already ubiquitous, and programmatically flexible foundation is an ideal option for discovery of AI agents. In this work, we propose an illustration and rationale for the basic semantics that discovery for AI agents will require. We argue that three key evaluation criteria will become paramount: navigational completeness (the extent to which the necessary metadata, with elements like trust, is included in a discovery solution), lookup complexity, and transaction performance (e.g., latency, speed, or recency). Using data about 119,757 real-world service endpoints and multiple agent tooling ecosystems, we empirically evaluate the first of these considerations to illustrate the appropriateness of using DNS for AI agent discovery. Our results show the size and amount of data necessary are well within the range of a single DNS UDP transaction, whose latency can be on the order of milliseconds. Our evaluations illustrate a promising path toward enabling AI agent discoverability at the Internet's scale, and thereby accelerating secure, stable, and resilient AI agent deployments.