{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T02:38:49Z","timestamp":1776998329395,"version":"3.51.4"},"reference-count":28,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T00:00:00Z","timestamp":1776297600000},"content-version":"vor","delay-in-days":15,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100016109","name":"Taishan Industry Leading Talents","doi-asserted-by":"publisher","award":["tscx202408127"],"award-info":[{"award-number":["tscx202408127"]}],"id":[{"id":"10.13039\/501100016109","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province","doi-asserted-by":"publisher","award":["ZR2022LZH018"],"award-info":[{"award-number":["ZR2022LZH018"]}],"id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Concurrency and Computation"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Cross\u2010architecture code migration has become essential as data centers transition from homogeneous x86 systems to heterogeneous \u201cone\u2010cloud, multi\u2010chip\u201d infrastructures that include ARM64, RISC\u2010V, and domestic processors. Traditional approaches, such as manual refactoring and rule\u2010based rewriting, face challenges in maintaining semantic correctness, scalability, and explainability. This paper presents an interactive, question\u2010answering (QA)\u2010driven framework that uses a frozen large language model (LLM) as a semantic reasoning engine. The framework combines static analysis, AST\u2010based semantic\u2010distance modeling, and a self\u2010evolving rule base for validated transformations, ensuring transparency, explainability, and architecture\u2010aware migration. It supports multiple languages (C++, Python, Java) and ISAs (x86, ARM64, RISC\u2010V) without the need for fine\u2010tuning the LLM. Evaluation on 30 real\u2010world codebases shows an average migration accuracy of 92.4%, approaching expert\u2010level performance (95.1%), with a 4.2\u00d7 reduction in migration errors and significant reduction in developer time (from 20\u201325\u2009h to 8\u2009h). These results demonstrate that the QA\u2010driven, LLM\u2010based migration framework significantly improves efficiency, accuracy, and scalability.<\/jats:p>","DOI":"10.1002\/cpe.70705","type":"journal-article","created":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T08:38:01Z","timestamp":1776328681000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Interactive\n                    <scp>LLM<\/scp>\n                    \u2010Driven Framework for Cross\u2010Architecture Code Migration: Balancing Efficiency, Accuracy, and Explainability"],"prefix":"10.1002","volume":"38","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5228-8139","authenticated-orcid":false,"given":"Peng","family":"Wang","sequence":"first","affiliation":[{"name":"Inspur Group Co., Ltd  People's Republic of China"},{"name":"Jinan Inspur Data Technology Co., Ltd  People's Republic of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaiyuan","family":"Qi","sequence":"additional","affiliation":[{"name":"Inspur Group Co., Ltd  People's Republic of China"},{"name":"Jinan Inspur Data Technology Co., Ltd  People's Republic of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Zhen","sequence":"additional","affiliation":[{"name":"Inspur Group Co., Ltd  People's Republic of China"},{"name":"Jinan Inspur Data Technology Co., Ltd  People's Republic of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingheng","family":"Yan","sequence":"additional","affiliation":[{"name":"Inspur Group Co., Ltd  People's Republic of China"},{"name":"Jinan Inspur Data Technology Co., Ltd  People's Republic of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Guo","sequence":"additional","affiliation":[{"name":"Inspur Group Co., Ltd  People's Republic of China"},{"name":"Jinan Inspur Data Technology Co., Ltd  People's Republic of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,4,16]]},"reference":[{"key":"e_1_2_10_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2014.07.003"},{"key":"e_1_2_10_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/2499370.2462176"},{"key":"e_1_2_10_4_1","first-page":"75","volume-title":"International Symposium on Code Generation and Optimization","author":"Lattner C.","year":"2004"},{"key":"e_1_2_10_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/IWCEAA63616.2024.10823767"},{"key":"e_1_2_10_6_1","volume-title":"Proceedings of the 2011 IEEE 17th International Conference on Parallel and Distributed Systems (ICPADS 2011)","author":"Martinez G.","year":"2011"},{"key":"e_1_2_10_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10766\u2010012\u20100211\u2010z"},{"key":"e_1_2_10_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.385"},{"key":"e_1_2_10_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2007.30"},{"key":"e_1_2_10_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2002.1019480"},{"key":"e_1_2_10_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2017.24"},{"key":"e_1_2_10_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO.2019.8661197"},{"key":"e_1_2_10_13_1","unstructured":"N.Vasilache N.Goyal T.Theodoridis et al. \u201cTensor Comprehensions: Framework\u2010Agnostic High\u2010Performance Machine Learning Abstractions \u201darXiv (2018) https:\/\/doi.org\/10.48550\/arXiv.1802.04730."},{"key":"e_1_2_10_14_1","first-page":"2655","volume-title":"Proceeding of NAACL\u2010HLT 2021","author":"Ahmad W.","year":"2021"},{"key":"e_1_2_10_15_1","volume-title":"CodeT5: Identifier\u2010Aware Unified Pre\u2010Trained Encoder\u2010Decoder Models for Code Understanding and Generation","author":"Wang Y.","year":"2021"},{"key":"e_1_2_10_16_1","unstructured":"U.Alon O.Levy O.Levy andE.Yahav \u201ccode2seq: Generating Sequences From Structured Representations of Code \u201dICLR (2019) https:\/\/doi.org\/10.48550\/arXiv.1808.01400."},{"key":"e_1_2_10_17_1","unstructured":"E.Nijkamp B.Pang H.Hayashi et al. \u201cCodeGen: An Open Large Language Model for Code With Multi\u2010Turn Program Synthesis \u201darXiv Preprint arXiv:2203.13474 (2022) https:\/\/doi.org\/10.48550\/arXiv.2203.13474."},{"key":"e_1_2_10_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_2_10_19_1","unstructured":"D.Guo S.Ren S.Lu et al. \u201cGraphCodeBERT: Pre\u2010Training Code Representations With Data Flow \u201dICLR 2021 (2021) https:\/\/doi.org\/10.48550\/arXiv.2009.08366."},{"key":"e_1_2_10_20_1","doi-asserted-by":"crossref","unstructured":"D.Guo S.Ren S.Lu et al. \u201cUniXcoder: Unified Cross\u2010Modal Pre\u2010Training for Code Representation \u201darXiv Preprint arXiv:2203.03850 (2022) https:\/\/doi.org\/10.48550\/arXiv.2203.03850.","DOI":"10.18653\/v1\/2022.acl-long.499"},{"key":"e_1_2_10_21_1","unstructured":"M.Chen J.Tworek H.Jun et al. \u201cEvaluating Large Language Models Trained on Code \u201dNeurIPS 2021 2021 https:\/\/doi.org\/10.48550\/arXiv.2107.03374."},{"key":"e_1_2_10_22_1","unstructured":"M.Balog A. L.Gaunt M.Brockschmidt et al. \u201cDeepCoder: Learning to Write Programs \u201dICLR 2017 (2017) https:\/\/doi.org\/10.48550\/arXiv.1611.01989."},{"key":"e_1_2_10_23_1","unstructured":"E.Nijkamp B.Pang H.Hayashi et al. \u201cCodeGen2: Lessons for Training LLMs on Programming and Natural Languages \u201darXiv Preprint arXiv:2305.02309 (2023) https:\/\/doi.org\/10.48550\/arXiv.2305.02309."},{"key":"e_1_2_10_24_1","unstructured":"J.Austin A.Odena M.Nye et al. \u201cProgram Synthesis With Large Language Models \u201darXiv Preprint arXiv:2108.07732 (2021) https:\/\/doi.org\/10.48550\/arXiv.2108.07732."},{"key":"e_1_2_10_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00778\u2010019\u201000552\u20101"},{"key":"e_1_2_10_26_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.abq1158"},{"key":"e_1_2_10_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3212695"},{"key":"e_1_2_10_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.112"},{"key":"e_1_2_10_29_1","doi-asserted-by":"publisher","DOI":"10.1137\/0218082"}],"container-title":["Concurrency and Computation: Practice and Experience"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70705","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/cpe.70705","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cpe.70705","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T01:49:19Z","timestamp":1776995359000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/cpe.70705"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":28,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1002\/cpe.70705"],"URL":"https:\/\/doi.org\/10.1002\/cpe.70705","archive":["Portico"],"relation":{},"ISSN":["1532-0626","1532-0634"],"issn-type":[{"value":"1532-0626","type":"print"},{"value":"1532-0634","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"2026-01-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-04-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70705"}}