Laboratorio de Investigación y Formación en Informática Avanzada (LIFIA)(先进信息与计算研究培训中心);Facultad de Informática - Universidad Nacional de La Plata(拉普拉塔国立大学信息学院);Comisión de Investiación Científica - CIC Bs.As.(布宜诺斯艾利斯省科学研究委员会)
Jose Manuel Suarez, Luis Mariano Bibbo, Joaquin Bogado, Alenandro Fernandez
The rapid evolution of Quantum Development Kits (QDKs) introduces a specific form of technical debt that compromises code maintainability and hinders software reuse. In the specialized domain of Quantum Software Engineering (QSE), this challenge is intensified by the scarcity of high-quality training data and the high volatility of emerging frameworks, which often lead general-purpose Large Language Models (LLMs) to produce unreliable or hallucinated results. This paper proposes a hybrid approach integrating LLMs with Retrieval-Augmented Generation (RAG) to automate the migration of Qiskit code across versions. The proposed methodology enhances the precision and reliability of migration suggestions by leveraging an automatically generated taxonomy of migration scenarios as the structured, version-specific knowledge source to guide the models. The approach is implemented through an automated, extensible workflow evaluating LLMs (Google Gemini Flash-2.5 and OpenAI Gpt-oss-20b) under different retrieval schemes (unconstrained and restrictive). Results demonstrate that the taxonomy-based RAG architecture, particularly under the restrictive scheme, significantly reduces hallucinations and improves descriptive quality, with Google Gemini Flash-2.5 showing superior performance in detecting complex refactoring scenarios. These findings confirm the potential of this data-centric methodology to foster technological independence and provide robust, intelligent assistants that mitigate API obsolescence, ensuring the long-term availability of quantum algorithms within a rapidly shifting ecosystem and flattening the learning curve within Quantum Software Engineering (QSE).
Taxonomy of migration scenarios for Qiskit refactoring using LLMs
Universidad Nacional de La Plata, Facultad de Informática Laboratorio de Investigación y Formación en Informática Avanzada (LIFIA), Argentina(拉普拉塔国立大学计算机学院高级信息技术研究与培训实验室,阿根廷)
本研究面向 Qiskit 版本迁移中的量子代码重构问题,比较专家与 LLM 构建的分类体系并整合为统一框架,以支持 AI 辅助迁移和自动化重构评估。
LibRec: Benchmarking Retrieval-Augmented LLMs for Library Migration Recommendations
School of Computer and Computing Science, Hangzhou City University(杭州城市大学计算机与计算科学学院);Polytechnic Institute, Zhejiang University(浙江大学多技术学院);School of Computer Science, Shanghai Jiao Tong University(上海交通大学计算机科学学院);School of Computer Science and Technology, Harbin Institute of Technology(哈尔滨工业大学深圳学院);College of Computer Science and Technology, Huazhong University of Science and Technology(华中科技大学计算机科学与技术学院);School of Computing and Information Systems, Singapore Management University(新加坡管理大学计算机与信息科学学院);College of Computer Science and Technology, Zhejiang University(浙江大学计算机科学与技术学院)
CODEMENV: Benchmarking Large Language Models on Code Migration
Provable Responsible AI and Data Analytics (PRADA) Lab(可证明责任人工智能与数据分析实验室);King Abdullah University of Science and Technology(国王 Abdullah 科学与技术大学);Peking University(北京大学);South China University of Technology(华南理工大学)
MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions
State Key Lab of Processors, Institute of Computing Technology, CAS(处理器国家重点实验室,计算技术研究所,中国科学院);University of Chinese Academy of Sciences(中国科学院大学);Zhongguancun Laboratory(中关村实验室);Tsinghua University(清华大学)
VecIntrinBench: Benchmarking Cross-Architecture Intrinsic Code Migration for RISC-V Vector
Intelligent Software Research Center, Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所智能软件研究中心);University of Chinese Academy of Sciences(中国科学院大学)
FreshBrew: A Benchmark for Evaluating AI Agents on Java Code Migration
Google(谷歌);Max Planck Institut für Intelligente Systeme (MPI-IS)(马克斯·普朗克智能系统研究所);ELLIS Institute, Tübingen(图宾根ELLIS研究所);Salesforce;Gologic Inc(Gologic公司)
Can Language Models Go Beyond Coding? Assessing the Capability of Language Models to Build Real-World Systems
Nankai University(南开大学);Haihe Laboratory of Information Technology Application Innovation(海河信息技术应用创新实验室);Key Laboratory of Data and Intelligent System Security, Ministry of Education(教育部数据与智能系统安全重点实验室);Tianjin Key Laboratory of Software Experience and Human Computer Interaction(天津市软件体验与人机交互重点实验室);Tsinghua University(清华大学)
EmbedAgent: Benchmarking Large Language Models in Embedded System Development
University of Chinese Academy of Sciences(中国科学院大学);The Hong Kong University of Science and Technology(香港科学与技术大学);Peng Cheng Laboratory(鹏城实验室);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所)