cs.NISep 18, 2026

Semantics Delivery Network: Rethinking Web Retrieval Infrastructure for LLM Agents

Authors: Peichun Hua, Yunming Xiao

Organizations: The Chinese University of Hong Kong, Shenzhen, China

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

Abstract

Large language models (LLMs) increasingly ground their answers in proprietary data and live web content through both single-shot retrieval-augmented generation (RAG) and multi-turn agentic search. Yet the web path they use was built for human readers: search services return URLs and snippets ranked by generic relevance, and content delivery networks (CDNs) cache URL-addressed objects without knowing which passage an agent needs. LLMs instead consume short, semantically coherent passages - hereafter, chunks - selected for downstream utility rather than similarity alone, retrieve statefully across reasoning turns, and, as uncoordinated streams, repeatedly fetch, clean, chunk, and embed the same content. We argue that semantic chunk retrieval should become a first-class network-delivery abstraction, and propose the Semantics Delivery Network (SemDN): an origin-authorized, hierarchical substrate that indexes, searches, and caches web content at chunk granularity, serving clients and origins alike. SemDN is more than finer-grained caching: it must estimate missing or stale evidence without an explicit miss signal, let clients choose retrieval representations that origins need not see, and share state among clients with the same representation. Preliminary results show that page-first retrieval processes two to three orders of magnitude more content than agents consume, that agentic queries exhibit task-local chunk reuse invisible to URL caches, and that chunk delivery improves answer quality per context token. We organize an open research agenda around shareable retrieval state, hierarchical caching and refresh under coverage risk, and deployability, including incentives, privacy, and verifiability. Our code is available at: https://github.com/sarendis56/SemDN_HotNets26

Figures & tables

Figure 1. Today’s retrieval path versus SemDN. (a) A search engine returns URLs; the agent fetches whole pages through a semantics-agnostic CDN and extracts chunks itself. (b) SemDN answers the query with top- kk chunks from a shared index over enrolled origins, optionally with proofs; a coverage signal triggers discovery and enrollment.
Figure 2. CDF of decompressed content bytes per query over the top-5 URLs (live web, 100 queries); values in the text are medians.
Figure 3. Agentic locality (a,b) and answer quality (c). (a) Reuse-interval CDF for distinct chunks; shaded band shows 5–95% over 50 popularity-preserving, task-shuffled controls. (b) Bytes to origin per demand byte vs. edge cache capacity. (c) Answer quality vs. reader context budget (CRAG Task-3, n=600n{=}600 ).
More in this topic

Semantic Caching

Semantic caching reuses results for meaningfully similar queries to reduce the latency and cost of AI, retrieval, and database systems.

See all 22 papers

Explore similar work

CardsList
Apr 13, 2026

AgentWebBench: Benchmarking Multi-Agent Coordination in Agentic Web

Agentic Web is an emerging paradigm where autonomous agents help users use online information. As the paradigm develops, content providers are also deploying agents to manage their data and serve it through controlled interfaces. This shift moves information access from centralized retrieval to decentralized coordination. To study this setting, we introduce AgentWebBench, a benchmark that evaluates how well a user agent synthesizes answers by interacting with website-specific content agents. We evaluate four tasks that cover common web information needs, spanning ranked retrieval (web search, web recommendation) and open-ended synthesis (question answering, deep research). Across seven advanced LLMs and three coordination strategies, multi-agent coordination generally lags behind centralized retrieval as expected, because user agent cannot directly access the corpus, but the gap shrinks with model scale and can even outperform centralized retrieval on question answering. This benchmark also enables us to study properties of the emerging paradigm of the digital world. We find that decentralized access concentrates traffic toward a small set of websites, test time scaling improves both interaction reliability and task performance, and strong results require sufficient interactions guided by careful planning. Finally, our failure analysis suggests that user agents need better planning and answer synthesis, while content agents need more reliable retrieval and evidence quality. Code, data, and APIs are released on https://github.com/cxcscmu/AgentWebBench.

Shanshan Zhong, Kate Shen, Chenyan Xiong

Language Technologies Institute, School of Computer Science, Carnegie Mellon University · Anaxi Labs

Web Agent BenchmarksWeb AgentsMulti-Agent CoordinationLLM Agent Evaluation
AskPDF
May 31, 2026

Efficient RAG with Intent-Aware Retrieval and Semantics-Preserving Chunking

The demand for powerful instruction following and reasoning capability of large language models (LLMs) has promoted rapid development of retrieval-augmented generation (RAG). The RAG system assists LLM generation by retrieving chunks of query-fit supplementary knowledge from an external database. Conventional RAG systems, however, suffer from information insufficiency due to two factors, which are intent-agnostic retrieval and information fragmentation. Our work proposes a RAG framework, termed InSemRAG, that addresses these challenges via an iterative retrieve-and-check mechanism with two supporting modules, an intention-aware retriever (IAR) and semantics-preserving chunking (SPC). IAR implements a dynamic hybrid retrieval method that adaptively weights the retrieval channels based on the query intent, while SPC performs detection and reparation to the damaged evidence chunks to preserve the semantic integrity. To alleviate the computational latency brought by our iterative mechanism, we leverage small language models (SLMs). Extensive experiments across several benchmark datasets consistently demonstrate the competitiveness of our method against recent state-of-the-art RAG mechanisms. Particularly, our method achieves significant gains on multi-hop and evidence-sensitive tasks, with a 2.65-point improvement in F1 on HotPotQA and a 1.5-point increase in accuracy on FEVER. Our method also achieves competitive performance to Multi-Hop RAG with 4.32×\times lower latency with the utilization of SLM.

Fachrina Dewi Puspitasari, Chaoning Zhang, Jiaquan Zhang +6

School of Computer Science and Engineering, University of Electronic Science and Technology of China · Massachusetts General Hospital, Harvard University · Nota AI

Multi-Hop QADocument ChunkingRetrieval-Augmented GenerationInformation Retrieval
AskPDF
Nov 23, 2025

From Crawled to Published: A Publisher-Controlled Web Architecture for an AI-Native Internet

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.

Yixi Chen, Muhammad Bilal, Tie Ma +3

Information RetrievalAgentic RetrievalWeb Agents
AskPDF