mlsanityData to 14 Oct 2026

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

arXiv 2604.20860 ↗First posted 2 Mar 2026cs.IR cs.AIcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

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 textitevidence 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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 32 of its 44 references that are in the map. First posted on arXiv 2 Mar 2026.

Builds on

32 of 44 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Collab-RAG: Boosting Retrieval-Augmented Generation for Complex Question Answering via White-Box and Black-Box LLM Collaboration7 Apr
  2. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection17 Oct

Other references · 30

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,182
  4. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  5. 2021WebGPT: Browser-assisted question-answering with human feedbackcited by 1,745
  6. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  7. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  8. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
  9. 2017Crowdsourcing Multiple Choice Science Questionscited by 765
  10. 2023Making Retrieval-Augmented Language Models Robust to Irrelevant Contextcited by 369
  11. 2024RAFT: Adapting Language Model to Domain Specific RAGcited by 262
  12. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 238
18 more
  1. 2023ReWOO: Decoupling Reasoning from Observations for Efficient Augmented Language Modelscited by 184
  2. 2024Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphscited by 119
  3. 2024AvaTaR: Optimizing LLM Agents for Tool Usage via Contrastive Reasoningcited by 72
  4. 2024Visual Agents as Fast and Slow Thinkerscited by 53
  5. 2024RATT: A Thought Structure for Coherent and Correct LLM Reasoningcited by 41
  6. 2024M-RAG: Reinforcing Large Language Model Performance through Retrieval-Augmented Generation with Multiple Partitionscited by 38
  7. 2025OmniRouter: Budget and Performance Controllable Multi-LLM Routingcited by 35
  8. 2024Probing-RAG: Self-Probing to Guide Language Models in Selective Document Retrievalcited by 29
  9. 2024Improving Retrieval Augmented Language Model with Self-Reasoningcited by 28
  10. 2025Synergizing RAG and Reasoning: A Systematic Reviewcited by 27
  11. 2024Open-RAG: Enhanced Retrieval-Augmented Reasoning with Open-Source Large Language Modelscited by 25
  12. 2024RARE: Retrieval-Augmented Reasoning Enhancement for Large Language Modelscited by 25
  13. 2024Learning to Plan for Retrieval-Augmented Large Language Models from Knowledge Graphscited by 24
  14. 2025MCTS-RAG: Enhancing Retrieval-Augmented Generation with Monte Carlo Tree Searchcited by 21
  15. 2025DualRAG: A Dual-Process Approach to Integrate Reasoning and Retrieval for Multi-Hop Question Answeringcited by 20
  16. 2025DeepSieve: Information Sieving via LLM-as-a-Knowledge-Routercited by 13
  17. 2024Query Routing for Homogeneous Tools: An Instantiation in the RAG Scenariocited by 10
  18. 2025Guarded Query Routing for Large Language Modelscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context
  2. 2026Route Before Retrieve: Activating Latent Routing Abilities of LLMs for RAG vs. Long-Context Selection
  3. 2024Retrieving, Rethinking and Revising: The Chain-of-Verification Can Improve Retrieval Augmented Generation
  4. 2026Fast and Faithful: Real-Time Verification for Long-Document Retrieval-Augmented Generation Systems
  5. 2026RAGRouter-Bench: A Dataset and Benchmark for Adaptive RAG Routing
  6. 2026ORDER: Task-Conditioned Routing for Retrieval-Augmented Generation
  7. 2026The Coverage Illusion: From Pre-retrieval Routing Failure to Post-retrieval Cascades in a Production RAG System
  8. 2026Cost-Aware Query Routing in RAG: Empirical Analysis of Retrieval Depth Tradeoffs