LaTeXTrans: Structured LaTeX Translation with Multi-Agent Coordination

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Zhu, Ziming, Wang, Chenglong, Xv, Haosong, Xing, Shunjie, Huo, Yifu, Tian, Fengning, Du, Quan, Yang, Di, Zhang, Chunliang, Xiao, Tong, Zhu, Jingbo
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915851463032832
author Zhu, Ziming
Wang, Chenglong
Xv, Haosong
Xing, Shunjie
Huo, Yifu
Tian, Fengning
Du, Quan
Yang, Di
Zhang, Chunliang
Xiao, Tong
Zhu, Jingbo
author_facet Zhu, Ziming
Wang, Chenglong
Xv, Haosong
Xing, Shunjie
Huo, Yifu
Tian, Fengning
Du, Quan
Yang, Di
Zhang, Chunliang
Xiao, Tong
Zhu, Jingbo
contents Despite the remarkable progress of modern machine translation (MT) systems on general-domain texts, translating structured LaTeX-formatted documents remains a significant challenge. These documents typically interleave natural language with domain-specific syntax, such as mathematical equations, tables, figures, and cross-references, all of which must be accurately preserved to maintain semantic integrity and compilability. In this paper, we introduce LaTeXTrans, a collaborative multi-agent system designed to address this challenge. LaTeXTrans ensures format preservation, structural fidelity, and terminology consistency through six specialized agents: 1) a Parser that decomposes LaTeX into translation-friendly units via placeholder substitution and syntax filtering; 2) a Translator, Validator, Summarizer, and Terminology Extractor that work collaboratively to ensure context-aware, self-correcting, and terminology-consistent translations; 3) a Generator that reconstructs the translated content into well-structured LaTeX documents. Experimental results show that LaTeXTrans outperforms mainstream MT systems in both translation accuracy and structural preservation. The source code, the online demonstration platform, and a demo video are publicly available.
format Preprint
id arxiv_https___arxiv_org_abs_2508_18791
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LaTeXTrans: Structured LaTeX Translation with Multi-Agent Coordination
Zhu, Ziming
Wang, Chenglong
Xv, Haosong
Xing, Shunjie
Huo, Yifu
Tian, Fengning
Du, Quan
Yang, Di
Zhang, Chunliang
Xiao, Tong
Zhu, Jingbo
Computation and Language
Despite the remarkable progress of modern machine translation (MT) systems on general-domain texts, translating structured LaTeX-formatted documents remains a significant challenge. These documents typically interleave natural language with domain-specific syntax, such as mathematical equations, tables, figures, and cross-references, all of which must be accurately preserved to maintain semantic integrity and compilability. In this paper, we introduce LaTeXTrans, a collaborative multi-agent system designed to address this challenge. LaTeXTrans ensures format preservation, structural fidelity, and terminology consistency through six specialized agents: 1) a Parser that decomposes LaTeX into translation-friendly units via placeholder substitution and syntax filtering; 2) a Translator, Validator, Summarizer, and Terminology Extractor that work collaboratively to ensure context-aware, self-correcting, and terminology-consistent translations; 3) a Generator that reconstructs the translated content into well-structured LaTeX documents. Experimental results show that LaTeXTrans outperforms mainstream MT systems in both translation accuracy and structural preservation. The source code, the online demonstration platform, and a demo video are publicly available.
title LaTeXTrans: Structured LaTeX Translation with Multi-Agent Coordination
topic Computation and Language
url https://arxiv.org/abs/2508.18791