LaTeXTrans: Structured LaTeX Translation with Multi-Agent Coordination

TL;DR

LaTeXTrans is a multi-agent system that improves the translation of LaTeX documents by ensuring structural fidelity, terminology consistency, and format preservation, outperforming existing machine translation systems.

Contribution

The paper introduces LaTeXTrans, a novel multi-agent framework specifically designed for translating structured LaTeX documents with high fidelity and accuracy.

Findings

Outperforms mainstream MT systems in translation accuracy

Ensures structural fidelity and format preservation in LaTeX translation

Demonstrates effectiveness through experimental results

Abstract

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.