ElixpoResearch
← Research index

preprint / not peer reviewed

A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware

By

Ayushman Bhattacharya, Nihal Gazi

Published · doi:10.48550/arXiv.2609.05463

Abstract

OreoLook presents a three-layer cache for session context, semantically equivalent queries, and URL embeddings in an open LLM answer engine operating on commodity CPU infrastructure.

Source code ↗Publication record ↗BibTeX ↓

Reproducibility

Evidence available for inspection

The implementation, interactive Space, paper, and evaluation dataset are public; the arXiv record states that code availability is by request, so the complete paper-specific reproduction path is not yet documented.

Authors and affiliations

  • Ayushman Bhattacharya
  • Nihal Gazi

Artifact licenses

Citation record

Citation and persistent identifiers

Bhattacharya and Gazi. A Three-Layer Caching Architecture for Low-Latency LLM Web Search on Commodity CPU Hardware. arXiv:2609.05463 (2026).

Download BibTeX →Open DOI record →