RealRoute: Dynamic Query Routing System via Retrieve-then-Verify Paradigm

TL;DR

RealRoute introduces a robust retrieve-then-verify framework for dynamic query routing across heterogeneous sources, improving factual grounding in multi-hop retrieval tasks with an open-source toolkit.

Contribution

It shifts from predictive source routing to a retrieve-then-verify paradigm, enhancing evidence completeness and factual accuracy in retrieval-augmented generation.

Findings

Outperforms predictive routing baselines in multi-hop reasoning tasks.

Ensures evidence completeness through parallel, source-agnostic retrieval.

Provides real-time visualization and verification of the routing process.

Abstract

Despite the success of Retrieval-Augmented Generation (RAG) in grounding LLMs with external knowledge, its application over heterogeneous sources (e.g., private databases, global corpora, and APIs) remains a significant challenge. Existing approaches typically employ an LLM-as-a-Router to dispatch decomposed sub-queries to specific sources in a predictive manner. However, this "LLM-as-a-Router" strategy relies heavily on the semantic meaning of different data sources, often leading to routing errors when source boundaries are ambiguous. In this work, we introduce RealRoute System, a framework that shifts the paradigm from predictive routing to a robust Retrieve-then-Verify mechanism. RealRoute ensures \textit{evidence completeness through parallel, source-agnostic retrieval, followed by a dynamic verifier that cross-checks the results and synthesizes a factually grounded answer}. Our demonstration allows users to visualize the real-time "re-routing" process and inspect the verification chain across multiple knowledge silos. Experiments show that RealRoute significantly outperforms predictive baselines in the multi-hop Rag reasoning task. The RealRoute system is released as an open-source toolkit with a user-friendly web interface. The code is available at the URL: https://github.com/Joseph1951210/RealRoute.