Large language models have transformed AI-assisted software engineering, but current research remains biased toward high-resource languages such as Python, with weaker performance in languages like Rust and OCaml. Since real-world systems are inherently polyglot, robust multilingual code intelligence is crucial. This survey focuses on two key tasks: multilingual code generation from shared natural-language requirements, and multilingual code translation that preserves semantics across languages. It reviews representative methods, benchmarks, and evaluation metrics, and highlights challenges and opportunities for trustworthy cross-language generalization.
@article{arxiv.2604.25960,
title = {Large Language Models for Multilingual Code Intelligence: A Survey},
author = {Chao Jiang and Dugang Liu and Cheng Wen and Zhiwu Xu and Hua Zheng and Muhammad Sadiq and Jawwad Ahmed Shamsi and Shengchao Qin and Zhong Ming},
journal= {arXiv preprint arXiv:2604.25960},
year = {2026}
}