Metraipolis › archive › dc_a5889c33bc4c

Semantics Delivery Network: Rethinking Web Retrieval Infrastructure for LLM Agents — arXiv:2609.22486

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.22486
License (as archived)
CC0-1.0
Archived
2026-10-09T07:08:12.434Z
SHA-256 of the archived text
fc6e6396b5704f19a40a6584878f18c03bd102c1529fbf3d80b70be28becc6ff
Stable URL of this page
https://metraipolis.com/documento/dc_a5889c33bc4c

How to cite

Semantics Delivery Network: Rethinking Web Retrieval Infrastructure for LLM Agents — arXiv:2609.22486 — arXiv (en), https://arxiv.org/abs/2609.22486 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a5889c33bc4c (Metraipolis archive dc_a5889c33bc4c, sha256 fc6e6396b5704f19a40a6584878f18c03bd102c1529fbf3d80b70be28becc6ff)
BibTeX
@misc{dca5889c33bc4c,
  title = {Semantics Delivery Network: Rethinking Web Retrieval Infrastructure for LLM Agents — arXiv:2609.22486},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.22486},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a5889c33bc4c; sha256 fc6e6396b5704f19a40a6584878f18c03bd102c1529fbf3d80b70be28becc6ff},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22486. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models (LLMs) increasingly rely on external sources when answering questions that require proprietary information or up-to-date live web content, through both traditional single-shot retrieval-augmented generation (RAG) and multi-turn agentic RAG. Yet today's web infrastructure is still built for human clients. Given a query, current search services return a list of URLs and snippets ranked for generic relevance; content delivery networks (CDNs) cache URL-addressed objects (texts, images, videos, etc.) without knowing which passage an agent needs. LLMs, in contrast, consume short, semantically coherent passages, hereafter "chunks", selected for downstream task utility rather than similarity alone, and may retrieve statefully across reasoning turns. Uncoordinated agents also repeat search, data acquisition, and semantic processing, duplicating work that could be shared. We argue that semantic chunk retrieval should become a first-class network-delivery abstraction. We propose Semantics Delivery Network (SemDN): an origin-authorized, hierarchical edge substrate that indexes, searches, and smart-caches web content at chunk granularity. SemDN serves agents on behalf of participating websites, amortizes data acquisition and processing across agents, and supports tenant-specific retrieval policies. Because, unlike URL caching, semantic retrieval provides no explicit miss signal, SemDN must estimate when its enrolled corpus may be incomplete or stale and trigger scoped discovery or refresh. It raises open questions about shareable retrieval state, hierarchical caching, coverage risk, and deployment. Our preliminary probes reveal a large gap between page content processed and chunks consumed, substantial task-local reuse, and higher answer quality per context token from chunk delivery.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-22 in cs.LG).
Categorie arXiv: Networking and Internet Architecture (cs.NI) ; Information Retrieval (cs.IR); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.22486 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T06:58:09.511Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).