AI Tool Discovery at Scale: All You Need is DNS
AI Tool Discovery at Scale: All You Need is DNS
大规模 AI 工具发现：DNS 足矣
Abstract: The coming era of autonomous AI agents demands a discovery mechanism capable of navigating millions of tools, yet existing solutions buckle under O(N) complexity and centralized governance. Instead of building another fragile overlay, we propose ToolDNS, a radical framework that retrofits semantic tool discovery onto the Internet’s most resilient substrate: the Domain Name System (DNS).
摘要： 自主 AI 智能体时代的到来，要求一种能够从数百万个工具中进行导航的发现机制，然而现有的解决方案在 O(N) 复杂度和中心化治理下显得力不从心。我们没有选择构建另一个脆弱的覆盖层，而是提出了 ToolDNS，这是一个激进的框架，它将语义工具发现功能改造并植入到互联网最稳健的基础设施中：域名系统（DNS）。
By embedding functional intent and organizational trust into a hierarchical namespace, ToolDNS transforms an expensive semantic search into a series of lightweight, O(log N) name resolutions. We introduce three protocol-compliant enhancements to enable decentralized governance and semantic pruning: partially unfolded names, EDNS0 intent payloads, and logical subdomains.
通过将功能意图和组织信任嵌入到分层命名空间中，ToolDNS 将昂贵的语义搜索转化为一系列轻量级的 O(log N) 名称解析。我们引入了三种符合协议的增强功能，以实现去中心化治理和语义剪枝：部分展开名称（partially unfolded names）、EDNS0 意图负载（EDNS0 intent payloads）以及逻辑子域（logical subdomains）。
To rigorously evaluate this approach across the fragmented tooling landscape, we construct and release a large-scale heterogeneous benchmark comprising 33,688 real-world tools spanning MCP, A2A, RESTful, and Skill protocols. On this dataset, ToolDNS slashes the per-query search space by 95.26% while matching state-of-the-art retrieval accuracy.
为了在碎片化的工具生态中严格评估该方法，我们构建并发布了一个大规模异构基准测试集，包含 33,688 个涵盖 MCP、A2A、RESTful 和 Skill 协议的真实世界工具。在该数据集上，ToolDNS 将单次查询的搜索空间缩减了 95.26%，同时保持了与当前最先进水平相当的检索准确率。
Furthermore, its UDP-native design reduces discovery latency by orders of magnitude compared to HTTP-based registries. Our work demonstrates that scalable AI interoperability requires not more middleware, but a smarter utilization of the infrastructure already beneath our feet.
此外，其原生 UDP 设计使发现延迟比基于 HTTP 的注册中心降低了几个数量级。我们的研究表明，可扩展的 AI 互操作性并不需要更多的中间件，而是需要更智能地利用我们脚下现有的基础设施。