[
    {
        "id": "osp-20341",
        "type": "article-journal",
        "title": "Breaking Babel: A Self-Evolving Multi-Agent System for Long-Form Subtitle Translation",
        "author": [
            {
                "family": "Jin",
                "given": "Haibo"
            },
            {
                "family": "Li",
                "given": "Xinjie"
            },
            {
                "family": "Sadoughi",
                "given": "Najmeh"
            },
            {
                "family": "Liu",
                "given": "Yang"
            },
            {
                "family": "Wang",
                "given": "Yibo"
            },
            {
                "family": "Liu",
                "given": "Zhu"
            },
            {
                "family": "Liu",
                "given": "Yuzong"
            }
        ],
        "URL": "https://omanscience.com/en/articles/breaking-babel-a-self-evolving-multi-agent-system-for-long-form-subtitle-translation",
        "language": "en",
        "issued": {
            "date-parts": [
                [
                    2026
                ]
            ]
        },
        "abstract": "Long-form subtitle translation requires reasoning over discourse and cultural context spanning episodes or entire series, while maintaining consistent terminology and style. Existing single-LLM methods are largely sentence-level, and multi-agent systems often use static workflows that do not adapt to scene complexity or production context. We propose SMART, a Self-evolving Multi-Agent system for long-foRm subtitle Translation. During test-time training, SMART builds persistent series-level memory and translates a subset of sentences through a dynamic router and Mixture-of-Agents layer with tools for terminology verification, subtitle constraint validation, and contextual retrieval. A judge-refiner loop scores candidates and uses textual critiques to update agent prompts and routing policies without retraining the underlying LLMs. During test-time inference, the evolved configuration translates the remaining series. We also introduce Subtitle Arena, covering 14 genres, 2--198 episodes per series, production years 1959--2023, and 15 target locales, together with SubMQM, a subtitle-adapted MQM framework with seven dimensions and 19 error categories. SMART achieves the best overall MQM score in all 15 Subtitle Arena directions, reducing average penalty by 6.9% over the strongest competing agent system. On a public benchmark, MuSC, SMART obtains the best model result across all 4 language pairs. SMART also achieves the best result in human evaluation with an overall score of 4.50/5."
    }
]