@InProceedings{giraud-gargett:2026:wmt2,
  author    = {Giraud, Jurgi  and  Gargett, Andrew},
  title     = {Agenteak: A Multi-Agent Pipeline for Terminology-Constrained Spanish-Basque Translation},
  booktitle      = {Proceedings of the Eleventh Conference on Machine Translation},
  month          = {October},
  year           = {2026},
  address        = {Budapest, Hungary},
  publisher      = {Association for Computational Linguistics},
  pages     = {1798--1807},
  abstract  = {This paper describes the OpenU's submission to the WMT26 Terminology Translation Task for Spanish into Basque (Track 1), covering the automotive and energy domains. We present AGENTEAK, a multi-agent system built on LangGraph in which three compact open-weight models (4-8B parameters) cooperate: a reasoning model that selects and disambiguates the terminology relevant to each segment, a domain fine-tuned translation model, and a verification model that checks and repairs terminology in the draft translation. To adapt the translator, we mined in-domain Spanish-Basque bitext from Wikipedia using multilingual sentence embeddings and complemented the data with in-domain synthetic parallel paragraphs generated by an instruction-tuned Basque LLM. Domain-tagged fine-tuning improves the base model by up to 10.4 BLEU and 3.9 COMET points on our in-domain test sets. On the shared task data, supplying the pipeline with correct terminology raises terminology success rate from 0.613 to 0.757 (automotive) and from 0.601 to 0.774 (energy).},
  url       = {https://aclanthology.org/2026.wmt-1.114}
}