ZeroRAG: Adaptive Semantic Peer Routing for Decentralized Retrieval-Augmented Generation

原文：ZeroRAG: Adaptive Semantic Peer Routing for Decentralized Retrieval-Augmented Generation

作者：Petru Neague, Quinten Stokkink, Martijn de Vos, Rafael Pires, Mathis Randl, Anne-Marie Kermarrec, Johan Pouwelse

来源：arXiv cs.DC（分布式并行）

正文

Computer Science > Distributed, Parallel, and Cluster Computing

arXiv:2611.07928v1 (cs)

[Submitted on 5 Nov 2026]

Title:ZeroRAG: Adaptive Semantic Peer Routing for Decentralized Retrieval-Augmented Generation

Authors:Petru Neague, Quinten Stokkink, Martijn de Vos, Rafael Pires, Mathis Randl, Anne-Marie Kermarrec, Johan Pouwelse

View a PDF of the paper titled ZeroRAG: Adaptive Semantic Peer Routing for Decentralized Retrieval-Augmented Generation, by Petru Neague and 6 other authors

View PDF

HTML (experimental)

Abstract:Retrieval-augmented generation (RAG) is a standard approach to enhance the reliability of large language model (LLM) outputs by retrieving documents relevant to a query and supplying them in the LLM prompt. Today’s RAG systems collect, index, and serve these documents from centralized stores. In practice, however, documents are owned by organizations, devices, and individuals who cannot or will not surrender custody of them to a central party, e.g., because of privacy, copyright or regulatory compliance. Existing modern decentralized retrieval techniques either reintroduce a coordinating authority, or rely on a global data structure that requires continuous network-wide coordination (e.g., DHTs). We present ZeroRAG, a decentralized routing layer for document retrieval in RAG that performs semantic query routing across an overlay of peers with- out global data structures or centralized orchestration. Documents remain with the peers that own them, and each peer keeps only lightweight local state: a bounded set of neighbor advertisements and a cache of recently routed queries. Using these, ZeroRAG steers each query through a best-first walk that progressively rewires the overlay toward semantically relevant neighbors, so recall improves over time as the network self-organizes. We evaluate ZeroRAG using three real-world workloads and two decentralized baselines. We find that ZeroRAG outperforms baselines in terms of recall and required network messages, approaches the recall and LLM answer accuracy of a centralized document store, self-heals after catastrophic peer failures, and scales to 100 000 peers.

Comments:

14 pages, 8 figures

Subjects:

Distributed, Parallel, and Cluster Computing (cs.DC); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Networking and Internet Architecture (cs.NI)

ACM classes:

H.3.3; H.2.4; C.2.4

Cite as:

arXiv:2611.07928 [cs.DC]

(or

arXiv:2611.07928v1 [cs.DC] for this version)

https://doi.org/10.48550/arXiv.2611.07928

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

主题

分布式计算 · 人工智能 · 信息检索 · cs.NI

由「前沿雷达」于 2026-11-05 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。