Interactive LLM ‐Driven Framework for Cross‐Architecture Code Migration: Balancing Efficiency, Accuracy, and Explainability
Concurrency and Computation: Practice and Experience · 2026-04 · 38 (8)
DOI: 10.1002/cpe.70705 ↗Kurz gefasst
Fachartikel in der Zeitschrift Concurrency and Computation: Practice and Experience, online erschienen am 16.04.2026. Verfasst von Peng Wang und 4 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Gefördert von: Taishan Industry Leading Talents, Natural Science Foundation of Shandong Province.
Abstract (Originalsprache)
Cross‐architecture code migration has become essential as data centers transition from homogeneous x86 systems to heterogeneous “one‐cloud, multi‐chip” infrastructures that include ARM64, RISC‐V, and domestic processors. Traditional approaches, such as manual refactoring and rule‐based rewriting, face challenges in maintaining semantic correctness, scalability, and explainability. This paper presents an interactive, question‐answering (QA)‐driven framework that uses a frozen large language model (LLM) as a semantic reasoning engine. The framework combines static analysis, AST‐based semantic‐distance modeling, and a self‐evolving rule base for validated transformations, ensuring transparency, explainability, and architecture‐aware migration. It supports multiple languages (C++, Python, Java) and ISAs (x86, ARM64, RISC‐V) without the need for fine‐tuning the LLM. Evaluation on 30 real‐world codebases shows an average migration accuracy of 92.4%, approaching expert‐level performance (95.1%), with a 4.2× reduction in migration errors and significant reduction in developer time (from 20–25 h to 8 h). These results demonstrate that the QA‐driven, LLM‐based migration framework significantly improves efficiency, accuracy, and scalability.
Förderung
- Taishan Industry Leading Talents
- Natural Science Foundation of Shandong Province
Zitieren
APA
Wang, P., Qi, K., Zhen, F., Yan, B., & Guo, T. (2026). Interactive LLM ‐Driven Framework for Cross‐Architecture Code Migration: Balancing Efficiency, Accuracy, and Explainability. Concurrency and Computation: Practice and Experience, 38(8). https://doi.org/10.1002/cpe.70705
Vancouver
Wang P, Qi K, Zhen F, Yan B, Guo T. Interactive LLM ‐Driven Framework for Cross‐Architecture Code Migration: Balancing Efficiency, Accuracy, and Explainability. Concurrency and Computation: Practice and Experience. 2026;38(8). doi:10.1002/cpe.70705
BibTeX
@article{Wang2026,
author = {Wang, Peng and Qi, Kaiyuan and Zhen, Feng and Yan, Bingheng and Guo, Tao},
title = {Interactive LLM ‐Driven Framework for Cross‐Architecture Code Migration: Balancing Efficiency, Accuracy, and Explainability},
journal = {Concurrency and Computation: Practice and Experience},
year = {2026},
volume = {38},
number = {8},
doi = {10.1002/cpe.70705}
}
EUVIMED