PulseAugur
EN
LIVE 01:17:25

New agent Loong enhances long document translation with adaptive context

By PulseAugur Editorial · [2 sources] ·

Researchers have developed Loong, a novel agent designed to improve long document translation for large language models. Loong utilizes a 3E memory module to store context in the form of summaries, sentence pairs, and entity records. It adaptively identifies optimal context for translation guidance through deep reasoning and reinforcement learning, overcoming the limitations of fixed context windows. Empirical evaluations show significant quality improvements in English-to-Chinese, German, and French translations, with gains up to 13.0 points across key metrics. AI

IMPACT Loong's adaptive context selection could improve the quality and efficiency of LLM-based translation for lengthy documents.

RANK_REASON The cluster contains a research paper detailing a new agent for long document translation.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

New agent Loong enhances long document translation with adaptive context

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Yutong Wang, Xuebo Liu, Derek F. Wong, Zhilin Li, Rongqing Jiang, Min Zhang, Shimin Tao, Daimeng Wei, Min Zhang ·

    Loong: A Human-Like Long Document Translation Agent with Observe-and-Act Adaptive Context Selection

    arXiv:2605.30274v1 Announce Type: cross Abstract: Document-level translation remains one of the most challenging tasks for large language models, which are constrained by limited context windows that impede global cohesion, while simultaneously suffering from redundant contextual…

  2. arXiv cs.AI TIER_1 English(EN) · Min Zhang ·

    Loong: A Human-Like Long Document Translation Agent with Observe-and-Act Adaptive Context Selection

    Document-level translation remains one of the most challenging tasks for large language models, which are constrained by limited context windows that impede global cohesion, while simultaneously suffering from redundant contextual information that degrades translation quality. To…

RELATED ENTITIES

RELATED TOPICS