IRB-MT at WMT25 Terminology Translation Task: Metric-guided Multi-agent Approach

AbstractTerminology-aware machine translation (MT) is needed in case of specialized domains such as science and law. Large Language Models (LLMs) have raised the level of state-of-art performance on the task of MT, but the problem is not completely solved, especially for use-cases requiring precise terminology translations. We participate in the WMT25 Terminology Translation Task with an LLM-based multi-agent system coupled with a custom terminology-aware translation quality metric for the selection of the final translation. We use a number of smaller open-weights LLMs embedded in an agentic “translation revision” workflow, and we do not rely on data- and compute-intensive fine-tuning of models. Our evaluations show that the system achieves very good results in terms of both MetricX-24 and a custom TSR metric designed to measure the adherence to predefined term mappings.