AISTRAL：面向 AI 原生互联网的发布者可控 Web 架构

View PDF HTML (experimental)

Abstract:AI agents, not humans, are becoming the web's primary consumers, yet the web still ships content structured for human browsing, with no native way for publishers to expose the semantic units within it. Access is therefore mediated by a handful of AI providers that crawl, chunk, and index content unilaterally, leaving publishers little control over how their content is represented, retrieved, or attributed. We argue this is a structural problem, not one better chunking or retrieval algorithms can solve. The web lacks a native layer for publisher-controlled semantic discovery and retrieval. We propose AISTRAL, an AI-Native Internet architecture that supplies this layer. Publishers expose semantically meaningful units (e.g., passages, claims, tables) through explicit, policy-governed interfaces they control, and a web-native semantic resolver, analogous to DNS but operating over meaning rather than location, lets agents discover relevant sources before retrieving fine-grained content directly from publishers. Our end-to-end prototype matches or exceeds representative centralized retrieval pipelines in answer quality, with up to 4.2x higher accuracy on large, specialized document collections. Against a public web-search agent, it answers up to 4.2x more questions correctly, while moving 2.9-41x less data per query. Because retrieval terminates at publisher-operated servers, attribution, provenance, and usage policies travel with the content, realigning incentives across the web ecosystem.

Subjects:	Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
ACM classes:	I.2; C.2.1
Cite as:	arXiv:2511.18354 [cs.NI]
	(or arXiv:2511.18354v2 [cs.NI] for this version)
	https://doi.org/10.48550/arXiv.2511.18354 arXiv-issued DOI via DataCite

Submission history

From: Muhammad Bilal [view email]
[v1] Sun, 23 Nov 2025 09:01:22 UTC (121 KB)
[v2] Tue, 20 Oct 2026 14:26:26 UTC (281 KB)