# RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering

Source: [RouterKGQA: Specialized--General Model Routing for Constraint-Aware Knowledge Graph Question Answering](<https://www.sota2.com/research/paper/69c0c8ef0636e5bf4afc3ac8>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-03-24T05:00:03.763Z

Authors: Bo Yuan, Hexuan Deng, Xuebo Liu, Min Zhang

Published: 2026-03-20T15:01:57.000Z

## Abstract

Knowledge graph question answering (KGQA) is a promising approach for mitigating LLM hallucination by grounding reasoning in structured and verifiable knowledge graphs. Existing approaches fall into two paradigms: retrieval-based methods utilize small specialized models, which are efficient but often produce unreachable paths and miss implicit constraints, while agent-based methods utilize large general models, which achieve stronger structural grounding at substantially higher cost. We propose RouterKGQA, a framework for specialized--general model collaboration, in which a specialized model generates reasoning paths and a general model performs KG-guided repair only when needed, improving performance at minimal cost. We further equip the specialized with constraint-aware answer filtering, which reduces redundant answers. In addition, we design a more efficient general agent workflow, further lowering inference cost. Experimental results show that RouterKGQA outperforms the previous best by 3.57 points in F1 and 0.49 points in Hits@1 on average across benchmarks, while requiring only 1.15 average LLM calls per question. Codes and models are available at https://github.com/Oldcircle/RouterKGQA.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Knowledge Graph Question Answering on WebQSP (Performance and Cost Analysis)](<https://www.sota2.com/research/sota/knowledge-graph-question-answering-on-webqsp-performance-and-cost-analysis.md>): Knowledge Graph Question Answering; WebQSP; Hits@1: 91.15.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.20017>)

[PDF](<https://arxiv.org/pdf/2603.20017.pdf>)