[KongchangAI]
Paper

ZeroRAG

A decentralized routing layer for RAG document retrieval that performs semantic query routing over a peer-to-peer overlay network. It requires no global index or centralized coordination; nodes maintain only lightweight local state (neighbor advertisement sets and query caches) and achieve self-organization and self-healing through best-first walks and dynamic rewiring.

Timeline (last 90 days)

Nov 6

ZeroRAG is a decentralized routing layer for RAG document retrieval that performs semantic query routing over an overlay network of peer nodes, requiring neither a global data structure nor centralized orchestration.

Unverified50%
Nov 6

In ZeroRAG, each node maintains only two kinds of lightweight local state: a bounded set of neighbor advertisements and a cache of recently routed queries.

Unverified50%
Nov 6

ZeroRAG uses a best-first walk to forward queries step by step and continuously rewires the overlay network during the process, causing neighbor relationships to evolve toward semantic relatedness.

Unverified50%
Nov 6

ZeroRAG's recall improvement depends on network self-organization driven by accumulated queries, so cold-start quality directly determines whether the system can enter a virtuous cycle.

Unverified50%
Nov 6

The paper evaluates ZeroRAG using three real workloads and two decentralized baselines.

Unverified50%
Nov 6

ZeroRAG outperforms both baselines on both recall and network message overhead.

Unverified50%
Nov 6

ZeroRAG approaches the recall and LLM answer accuracy of centralized document storage.

Unverified50%
Nov 6

ZeroRAG can self-heal after catastrophic node failures because there is no global index acting as a single point of dependency.

Unverified50%
Nov 6

ZeroRAG's experiments scale to 100,000 nodes, validating the feasibility of this approach in large-scale peer-to-peer networks.

Unverified50%
Nov 6

ZeroRAG suggests a different RAG deployment paradigm: data does not have to move, and retrieval capability can be distributed through a network protocol.

Unverified50%

All Facts (10)

Unverified

ZeroRAG is a decentralized routing layer for RAG document retrieval that performs semantic query routing over an overlay network of peer nodes, requiring neither a global data structure nor centralized orchestration.

50%
Unverified

In ZeroRAG, each node maintains only two kinds of lightweight local state: a bounded set of neighbor advertisements and a cache of recently routed queries.

50%
Unverified

ZeroRAG uses a best-first walk to forward queries step by step and continuously rewires the overlay network during the process, causing neighbor relationships to evolve toward semantic relatedness.

50%
Unverified

ZeroRAG's recall improvement depends on network self-organization driven by accumulated queries, so cold-start quality directly determines whether the system can enter a virtuous cycle.

50%
Unverified

The paper evaluates ZeroRAG using three real workloads and two decentralized baselines.

50%
Unverified

ZeroRAG outperforms both baselines on both recall and network message overhead.

50%
Unverified

ZeroRAG approaches the recall and LLM answer accuracy of centralized document storage.

50%
Unverified

ZeroRAG can self-heal after catastrophic node failures because there is no global index acting as a single point of dependency.

50%
Unverified

ZeroRAG's experiments scale to 100,000 nodes, validating the feasibility of this approach in large-scale peer-to-peer networks.

50%
Unverified

ZeroRAG suggests a different RAG deployment paradigm: data does not have to move, and retrieval capability can be distributed through a network protocol.

50%

Source Articles