RealRoute: Dynamic Query Routing System via Retrieve-then-Verify Paradigm
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918462865014784 |
|---|---|
| author | Liu, Jiahe Yu, Qinkai Niu, Jingcheng Zhu, Xi He, Zirui Xiang, Zhen Yang, Fan Zhao, Jinman |
| author_facet | Liu, Jiahe Yu, Qinkai Niu, Jingcheng Zhu, Xi He, Zirui Xiang, Zhen Yang, Fan Zhao, Jinman |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_20860 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RealRoute: Dynamic Query Routing System via Retrieve-then-Verify Paradigm Liu, Jiahe Yu, Qinkai Niu, Jingcheng Zhu, Xi He, Zirui Xiang, Zhen Yang, Fan Zhao, Jinman Information Retrieval Artificial Intelligence 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. |
| title | RealRoute: Dynamic Query Routing System via Retrieve-then-Verify Paradigm |
| topic | Information Retrieval Artificial Intelligence |
| url | https://arxiv.org/abs/2604.20860 |