2026-10-05T21:32:54Z https://drops.dagstuhl.de/oai

oai:drops-oai.dagstuhl.de:28053 2026-10-05T06:44:06Z ddc:004 open_access

Why Industry Migrates and When It Trusts LLMs: A Practitioner Survey on LLM-Assisted Software Migration Chand, Sivajeet Lenz, Gedeon Funke, Patrick Zhu, Derui Pretschner, Alexander LLMs Code Migration Industrial Insights LLM-Assisted Code Translation Software migrations are frequent and high-stakes industrial activities. Although large language models (LLMs) are increasingly used in software development, their suitability for migration remains uncertain because migration requires semantic preservation, project-specific context, security, and production accountability. We investigate why practitioners undertake software migrations, what motivates and constrains the use of LLMs for migration, where LLM assistance is considered acceptable, and which factors determine trust in LLM-migrated code. We conducted a practitioner survey with 61 retained industry respondents, combining an internal industrial sample with an open professional survey. We analyzed closed and Likert-style items quantitatively and interpreted open-ended responses thematically. Migration was primarily framed as a bundled quality-risk activity: maintainability, scalability, and security were the dominant motives, while cost reduction rarely appeared as a standalone driver. Respondents valued LLMs mainly as accelerators for exploration, prototyping, and routine transformation, but not as autonomous migration agents. Acceptability was strongly bound by scope and control: 62.3% considered LLMs acceptable most of the time or almost always for single-file migration, compared with only 4.9% for entire-project migration. Trust depended chiefly on semantic correctness, project-context awareness, security, verification evidence, and provenance disclosure. Practitioners do not reject LLM-assisted migration outright; rather, they adopt a conditional trust model. LLMs are viewed as useful migration accelerators, but acceptable production use depends on bounded scope, human review, assurance evidence, traceability, and clear accountability. Schloss Dagstuhl – Leibniz-Zentrum für Informatik Sivajeet Chand and Gedeon Lenz and Patrick Funke and Derui Zhu and Alexander Pretschner 2026 Is Part Of LIPIcs, Volume 394, 20th International Symposium on Empirical Software Engineering and Measurement (ESEM 2026) InProceedings Text doc-type:ResearchArticle publishedVersion application/pdf doi:10.4230/LIPIcs.ESEM.2026.85 urn:nbn:de:0030-drops-280531 https://drops.dagstuhl.de/entities/document/10.4230/LIPIcs.ESEM.2026.85 eng https://creativecommons.org/licenses/by/4.0/legalcode