@inproceedings{liu-etal-2026-task,
    title = "Task-Aware {LLM} Routing with Multi-Level Task-Profile-Guided Data Synthesis for Cold-Start Scenarios",
    author = "Liu, Hui  and
      Zou, Bin  and
      Chen, Kecheng  and
      Liu, Jie  and
      Wang, Wenya  and
      Li, Haoliang",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1007/",
    pages = "22047--22076",
    ISBN = "979-8-89176-390-6",
    abstract = "Large language models (LLMs) exhibit substantial variability in performance and computational cost across tasks and queries, motivating routing systems that select models to meet user-specific cost{--}performance trade-offs. However, existing routers generalize poorly in cold-start scenarios where in-domain training data is unavailable. We address this limitation with a multi-level task-profile{--}guided data synthesis framework that constructs a hierarchical task taxonomy and produces diverse question{--}answer pairs to approximate the test-time query distribution. Building on this, we introduce TRouter, a task-type{--}aware router approach that models query-conditioned cost and performance via latent task-type variables, with prior regularization derived from the synthesized task taxonomy. This design enhances TRouter{'}s routing utility under both cold-start and in-domain settings. Across multiple benchmarks, we show that our synthesis framework alleviates cold-start issues and that TRouter delivers effective LLM routing."
}