ICAM-Trans: Implicit-Context-Aware Multi-Agent Framework for Function-Level Code Translation
ACM Transactions on Software Engineering and Methodology · 30.11.2026 · 35 (11) · 1-33
DOI: 10.1145/3810952 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 03.11.2026. Verfasst von Ruolin Chen und 4 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Science and Technology Planning Project of Guangdong Province, Guangdong Provincial Fund for Basic and Applied Basic Research—Regional Joint Fund Project, National Natural Science Foundation of China.
Abstract (Originalsprache)
With the rapid advancement of Large Language Models (LLMs), code translation has become a critical yet challenging task in software engineering. Existing evaluations of this task remain unreliable due to two key limitations: the absence of specialized function-level code translation benchmarks and flawed evaluation pipelines. Specifically, current pipelines lack post-processing mechanisms to extract target code from LLMs’ inherently unstable output formats, directly resulting in non-executable translations and false negatives in evaluation. To address these issues, we introduce FuncTransEval, an enhanced multilingual benchmark. It comprises 400 × 4 functions across four programming languages (Python, C++, Java, and JavaScript) and 12 bidirectional translation pairs, each paired with executable unit tests for fine-grained functional validation. Using FuncTransEval, we systematically assess LLMs’ true capabilities in code translation and identify their core limitations: inadequate understanding of the implicit information such as function logic, type specifications, and cross-language differences. To mitigate these shortcomings, we propose ICAM-Trans (Implicit-Context-Aware Multi-Agent Framework for function-level code translation). ICAM-Trans is a hierarchical, autonomous multi-agents architecture that explicitly uncovers and leverages these implicit contextual information during translation. It employs a Translation Orchestrate Agent (TOA) to autonomously coordinate four specialized Context Analysis Agents (CAAs), which conduct pre-translation analyses on different aspects. Insights from these analyses guide a Context-Aware Translation Agent (CTA) to generate semantically faithful target code. Experiments on FuncTransEval demonstrate that ICAM-Trans consistently outperforms strong baselines, validating its effectiveness in achieving high-fidelity and interpretable function-level code translation.
Förderung
- Science and Technology Planning Project of Guangdong Province
- Guangdong Provincial Fund for Basic and Applied Basic Research—Regional Joint Fund Project
- National Natural Science Foundation of China
- Guangdong Provincial Natural Science Foundation for Outstanding Youth Team Project
- Fundamental Research Funds for the Central Universities, South China University of Technology
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Chen, R., Wang, J., Cao, L., Cai, Y., & Zhao, M. (2026). ICAM-Trans: Implicit-Context-Aware Multi-Agent Framework for Function-Level Code Translation. ACM Transactions on Software Engineering and Methodology, 35(11), 1-33. https://doi.org/10.1145/3810952
Vancouver
Chen R, Wang J, Cao L, Cai Y, Zhao M. ICAM-Trans: Implicit-Context-Aware Multi-Agent Framework for Function-Level Code Translation. ACM Transactions on Software Engineering and Methodology. 2026;35(11):1-33. doi:10.1145/3810952
BibTeX
@article{Chen2026,
author = {Chen, Ruolin and Wang, Jiexin and Cao, Liuwen and Cai, Yi and Zhao, Mengchen},
title = {ICAM-Trans: Implicit-Context-Aware Multi-Agent Framework for Function-Level Code Translation},
journal = {ACM Transactions on Software Engineering and Methodology},
year = {2026},
volume = {35},
number = {11},
pages = {1--33},
doi = {10.1145/3810952}
}
EUVIMED