Who Has the Final Word? Designing Multi-Agent Collaborative Framework for Professional Translators

2026-02-21

AI Summary

This work addresses the limitations of existing translation tools, which typically rely on single-pass generation or optimization by a solitary agent and thus struggle to meet professional translators’ multifaceted requirements regarding accuracy, terminology, style, and audience adaptation. To overcome this, we propose CHORUS, a novel framework that integrates Multidimensional Quality Metrics (MQM) with a large language model–driven multi-agent system. CHORUS decomposes translation quality into specialized agents and enables human-AI collaboration through a translator-in-the-loop iterative refinement process, granting translators ultimate control over the workflow. This design significantly enhances support for professional translation practices. In preliminary user studies, six professional translators consistently rated CHORUS as producing higher-quality translations than both zero-shot and single-agent baseline approaches.

Technology Category

• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
• Multiagent Systems: Teamwork
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Recent advances in LLM based translation have led to renewed interest in fully automated systems, yet professional translators remain essential in high stakes domains where decisions about accuracy, terminology, style, and audience cannot be safely automated. Current tools are typically single shot generators or single-agent self-refiners, offering limited support for translator multidimensional decision making process and providing little structured leverage for translator input. We present CHORUS, a human-AI multiagent collaborative translation framework grounded in the Multidimensional Quality Metrics (MQM) framework, which decomposes quality dimensions into specialized agents and integrates their feedback into an iterative refinement loop controlled by the translator. A six-user preliminary study with professional translators found that CHORUS consistently outperforms zero-shot and single-agent baselines, showing that MQM-aligned multi-agent collaboration better supports professional translation workflows than autonomous generation.

Problem

• professional translation
• multi-agent collaboration
• translation quality
• human-AI interaction
• multidimensional decision making

Innovation

• multi-agent collaboration
• human-AI translation
• Multidimensional Quality Metrics (MQM)
• iterative refinement
• professional translation workflow