@inproceedings{keyu-etal-2026-bicsrouter,
    title = "{B}i{CSR}outer: Bi-Level Cross-System Routing for Utility-Aware {LLM} Inference",
    author = "Keyu, Mao  and
      Murata, Eiki  and
      Honda, Ukyo",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-form-platform/2026.findings-acl.947/",
    pages = "18979--18993",
    ISBN = "979-8-89176-395-1",
    abstract = "Selecting an appropriate LLM configuration for a given query is critical, yet existing routing frameworks operate within a single computational paradigm. To address this gap, we formalize the Cross-System Routing Problem, a hierarchical decision-making task that decomposes routing into intra-regime configuration selection and inter-regime system selection. Building on this, we propose BiCSRouter, a bi-level cross-system routing framework that integrates two orthogonal regimes: intensive reasoning via single-agent systems and extensive collaboration via multi-agent systems. BiCSRouter performs policy learning within each system and employs a lightweight inter-regime router that selects the optimal regime based on predicted performance and cost. Experiments on the MBPP and MATH benchmarks demonstrate that BiCSRouter outperforms 15 representative baselines across three types. On MBPP, compared to the performance ceiling of GPT-5, BiCSRouter achieves a 46{\%} reduction in cost with only a 2{\%} drop in accuracy. Finally, we show that BiCSRouter can extend to additional regimes, highlighting its generality as a cross-system routing framework."
}