UniOR-MT: An Agentic Pipeline for Terminology Translation

We present UniOR-MT, an agentic terminology-aware machine translation pipeline developed for the WMT 2026 Terminology Translation Shared Task. We compare five progressively enriched translation paths, each adding one component to isolate its individual contribution. We additionally submit a mixed system that selects, among the five candidate paths, the best candidate using a combined measure of terminology accuracy and document-level quality estimation. Evaluation results show that incorporating a bilingual glossary provides the most consistent benefit, while additional post-editing steps yield limited improvements, and can even degrade translation quality for Spanish--Basque in the official evaluation. The final system, which includes iterative QA feedback and a stronger fallback model, achieves the highest docCOMET scores in our internal evaluation.