AI Tool Discovery at Scale: All You Need is DNS

• URL: http://arxiv.org/abs/2607.18242v1
• Date: Sun, 19 Apr 2026 04:31:19 GMT
• Title: AI Tool Discovery at Scale: All You Need is DNS
• Abstract summary: ToolDNS is a radical framework that retrofits semantic tool discovery onto the Internet's most resilient substrate: the Domain Name System.<n>By embedding functional intent and organizational trust into a hierarchical, ToolDNS transforms an expensive semantic search into a series of lightweight, O(log N) name resolutions.<n>Our work demonstrates that scalable AI interoperability requires not more, but a smarter utilization of the infrastructure already beneath our feet.
• Score: 13.956883631679121
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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). 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. 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. 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.

Related papers

• SearchOS-V1: Towards Robust Open-Domain Information-Seeking Agent Collaboration [77.28003194268977]
  SearchOS is a system-level multi-agent framework that turns fragile, implicit search progress into explicit, persistent, and shared state.<n>Built on SOCM, SearchOS applies a pipeline-parallel scheduling mechanism that overlaps the execution of sub-agents.<n>SearchOS leads all metrics among the evaluated single- and multi-agent baselines.
  arXiv  Detail & Related papers  (2026-07-16T17:51:23Z)
• DNS-GT: A Graph-based Transformer Approach to Learn Embeddings of Domain Names from DNS Queries [6.172641282378335]
  DNS-GT is a novel Transformer-based model that learns embeddings for domain names from sequences of DNS queries.<n>Our experiments with real-world DNS data showcase the ability of our method to learn effective domain name representations.
  arXiv  Detail & Related papers  (2026-03-11T18:14:07Z)
• Nested Browser-Use Learning for Agentic Information Seeking [60.775556172513014]
  Information-seeking (IS) agents have achieved strong performance across a range of wide and deep search tasks, yet their tool use remains largely restricted to API-level snippet retrieval and URL-based page fetching.<n>We propose Nested Browser-Use Learning (NestBrowse), which introduces a minimal and complete browser-action framework that decouples interaction control from page exploration through a nested structure.
  arXiv  Detail & Related papers  (2025-12-29T17:59:14Z)
• WALT: Web Agents that Learn Tools [66.73502484310121]
  WALT is a framework that reverse-engineers latent website functionality into reusable invocable tools.<n>Rather than hypothesizing ad-hoc skills, WALT exposes robust implementations of automations already designed into websites.<n>On VisualWebArena and WebArena, WALT achieves higher success with fewer steps and less LLM-dependent reasoning.
  arXiv  Detail & Related papers  (2025-10-01T23:41:47Z)
• Beyond DNS: Unlocking the Internet of AI Agents via the NANDA Index and Verified AgentFacts [12.955380032776068]
  We describe the NANDA index architecture, which we envision as a means for discoverability, identifiability and authentication in the internet of AI agents.<n>We present an architecture where a minimal lean index resolves to dynamic, cryptographically verifiable AgentFacts.
  arXiv  Detail & Related papers  (2025-07-18T13:40:46Z)
• Upgrade or Switch: Do We Need a Next-Gen Trusted Architecture for the Internet of AI Agents? [12.116270471408216]
  The emerging Internet of AI Agents challenges existing web infrastructure designed for human-scale, reactive interactions.<n>This paper analyzes whether to upgrade existing infrastructure or implement purpose-built index architectures for autonomous agents.
  arXiv  Detail & Related papers  (2025-06-13T17:55:38Z)
• AgentDNS: A Root Domain Naming System for LLM Agents [7.480444282640687]
  AgentDNS is a root domain naming and service discovery system for Large Language Model (LLM) agents.<n>Inspired by the principles of the traditional DNS, AgentDNS introduces a structured mechanism for service registration, semantic service discovery, secure invocation, and unified billing.
  arXiv  Detail & Related papers  (2025-05-28T13:56:22Z)
• ZeroLM: Data-Free Transformer Architecture Search for Language Models [54.83882149157548]
  Current automated proxy discovery approaches suffer from extended search times, susceptibility to data overfitting, and structural complexity.<n>This paper introduces a novel zero-cost proxy methodology that quantifies model capacity through efficient weight statistics.<n>Our evaluation demonstrates the superiority of this approach, achieving a Spearman's rho of 0.76 and Kendall's tau of 0.53 on the FlexiBERT benchmark.
  arXiv  Detail & Related papers  (2025-03-24T13:11:22Z)
• A Matrix Factorization Based Network Embedding Method for DNS Analysis [2.1842847029116443]
  I explore the potential of network embedding to characterize DNS entities in passive network traffic logs.<n>I propose an MF-DNS-E (underlineMatrix-underlineFactorization-based underlineDNS underlineEmbedding) method to represent DNS entities.
  arXiv  Detail & Related papers  (2024-01-15T01:18:57Z)
• OTOv3: Automatic Architecture-Agnostic Neural Network Training and Compression from Structured Pruning to Erasing Operators [57.145175475579315]
  This topic spans various techniques, from structured pruning to neural architecture search, encompassing both pruning and erasing operators perspectives. We introduce the third-generation Only-Train-Once (OTOv3), which first automatically trains and compresses a general DNN through pruning and erasing operations. Our empirical results demonstrate the efficacy of OTOv3 across various benchmarks in structured pruning and neural architecture search.
  arXiv  Detail & Related papers  (2023-12-15T00:22:55Z)
• Neural network relief: a pruning algorithm based on neural activity [47.57448823030151]
  We propose a simple importance-score metric that deactivates unimportant connections. We achieve comparable performance for LeNet architectures on MNIST. The algorithm is not designed to minimize FLOPs when considering current hardware and software implementations.
  arXiv  Detail & Related papers  (2021-09-22T15:33:49Z)
• Optimized Random Forest Model for Botnet Detection Based on DNS Queries [8.641714871787595]
  Domain Name System (DNS) protocol has several security vulnerabilities. One promising solution to detect DNS-based botnet attacks is adopting machine learning (ML) based solutions. This paper proposes a novel optimized ML-based framework to detect botnets based on their corresponding DNS queries.
  arXiv  Detail & Related papers  (2020-12-16T16:34:11Z)
• PatDNN: Achieving Real-Time DNN Execution on Mobile Devices with Pattern-based Weight Pruning [57.20262984116752]
  We introduce a new dimension, fine-grained pruning patterns inside the coarse-grained structures, revealing a previously unknown point in design space. With the higher accuracy enabled by fine-grained pruning patterns, the unique insight is to use the compiler to re-gain and guarantee high hardware efficiency.
  arXiv  Detail & Related papers  (2020-01-01T04:52:07Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.