ACL 2025finding0 citations

TagRouter: Learning Route to LLMs through Tags for Open-Domain Text Generation Tasks

Zhou Chen, Zhiqiang Wei, Yuqi Bai, Xue Xiong, Jianmin Wu

Abstract

Model routing allocates queries to the suitable model, improving system performance while reducing costs. However, existing routing methods face practical limitations that hinder scalability in large-scale applications and struggle to keep up with the rapid growth of the large language model (LLM) ecosystem. To tackle these challenges, we propose TagRouter, a training-free model routing method designed to optimize the synergy among multiple LLMs for open-domain text generation tasks. Experimental results demonstrate that TagRouter outperforms 13 baseline methods, increasing the accept rate of system by 6.15% and reducing costs by 17.20%, achieving optimal cost-efficiency. Our findings provides the LLM community with an efficient and scalable solution for model ensembling, offering users an evolvable “super model.”

BibTeX
@inproceedings{chen-etal-2025-tagrouter,
    title = "{T}ag{R}outer: Learning Route to {LLM}s through Tags for Open-Domain Text Generation Tasks",
    author = "Chen, Zhou  and
      Wei, Zhiqiang  and
      Bai, Yuqi  and
      Xiong, Xue  and
      Wu, Jianmin",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2025.findings-acl.1110/",
    doi = "10.18653/v1/2025.findings-acl.1110",
    pages = "21539--21564",
    ISBN = "979-8-89176-256-5"
}