Are AI agents the new machine translation frontier? Challenges and opportunities of single- and multi-agent systems for multilingual digital communication

2025-04-17

AI Summary

To address the limitations of conventional machine translation (MT) in professional domains—namely insufficient accuracy, domain adaptability, and contextual awareness—this paper proposes and empirically validates a large language model (LLM)-based multi-agent collaborative translation paradigm. The approach systematically designs four specialized agents: translation, adequacy evaluator, fluency evaluator, and editor. These agents coordinate via task orchestration and a multi-stage quality feedback loop, augmented by domain-specific fine-tuning and prompt engineering tailored to legal texts. In legal translation experiments, the multi-agent system significantly outperforms both standard end-to-end MT and single-agent baselines across translation quality, terminology consistency, and contextual coherence, while also improving interpretability and controllability. The work contributes a novel, modular, and feedback-driven translation architecture for high-stakes domains and releases an open-source interactive demonstration system.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Machine Translation, Multilinguality, Cross-Lingual NLP
• Multiagent Systems: Multiagent Learning

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

The rapid evolution of artificial intelligence (AI) has introduced AI agents as a disruptive paradigm across various industries, yet their application in machine translation (MT) remains underexplored. This paper describes and analyses the potential of single- and multi-agent systems for MT, reflecting on how they could enhance multilingual digital communication. While single-agent systems are well-suited for simpler translation tasks, multi-agent systems, which involve multiple specialized AI agents collaborating in a structured manner, may offer a promising solution for complex scenarios requiring high accuracy, domain-specific knowledge, and contextual awareness. To demonstrate the feasibility of multi-agent workflows in MT, we are conducting a pilot study in legal MT. The study employs a multi-agent system involving four specialized AI agents for (i) translation, (ii) adequacy review, (iii) fluency review, and (iv) final editing. Our findings suggest that multi-agent systems may have the potential to significantly improve domain-adaptability and contextual awareness, with superior translation quality to traditional MT or single-agent systems. This paper also sets the stage for future research into multi-agent applications in MT, integration into professional translation workflows, and shares a demo of the system analyzed in the paper.

Problem

• Exploring AI agents' potential in machine translation systems.
• Comparing single- vs multi-agent systems for complex translation tasks.
• Evaluating multi-agent workflows for domain-specific translation quality improvement.

Innovation

• Multi-agent systems enhance machine translation accuracy
• Specialized AI agents collaborate for domain-specific tasks
• Pilot study demonstrates superior translation quality