@inproceedings{rosa-2026-multi,
    title = "Multi-Agent Orchestration for Terminology-Constrained Machine Translation in Industrial Localization",
    author = "Rosa, Emanuele Di",
    editor = "Li, Yunyao  and
      Rehm, Georg  and
      Tu, Mei",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 6: Industry Track)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-form-platform/2026.acl-industry.63/",
    pages = "917--926",
    ISBN = "979-8-89176-394-4",
    abstract = "Accurate terminology is a non-negotiable requirement in industrial localization processes: a single mistranslated domain term can violate contractual obligations and erode client trust.We present $AIDA\textsubscript{term}$, a deployed multi-agent LLM pipeline that orchestrates four specialized agents{---}Analysis, Translation, Post-editing, and Review{---}for terminology-constrained machine translation.The system introduces terminology-aware pre-analysis, explicit glossary injection at every pipeline stage, and a reasoning-enabled Review agent.We evaluate six configurations on the WMT25 Terminology Translation benchmark (Track{~}1: en$\to$de/es/ru, IT domain), enabling systematic ablation of each design choice.Our best configuration achieves 99.4{\%} average terminology accuracy while attaining the highest ChrF2++ scores across all three language pairs, outperforming all 20 systems submitted to the shared task.Unlike other multi-agent approaches in WMT25 that rely on generate-and-select strategies, $AIDA\textsubscript{term}$ is the first to apply a role-specialized sequential pipeline to terminology-constrained MT, and is deployed with native XLIFF integration for seamless CAT tool interoperability.The system processes thousands of terminology-constrained requests daily at a large localization provider."
}