[2603.24774] From Untestable to Testable: Metamorphic Testing in the Age of LLMs

Computer Science > Software Engineering arXiv:2603.24774 (cs) [Submitted on 25 Mar 2026] Title:From Untestable to Testable: Metamorphic Testing in the Age of LLMs Authors:Valerio Terragni View a PDF of the paper titled From Untestable to Testable: Metamorphic Testing in the Age of LLMs, by Valerio Terragni View PDF Abstract:This article discusses the challenges of testing software systems with increasingly integrated AI and LLM functionalities. LLMs are powerful but unreliable, and labeled ground truth for testing rarely scales. Metamorphic Testing solves this by turning relations among multiple test executions into executable test oracles. Comments: Subjects: Software Engineering (cs.SE); Artificial Intelligence (cs.AI) ACM classes: D.2.5; I.2.7 Cite as: arXiv:2603.24774 [cs.SE]   (or arXiv:2603.24774v1 [cs.SE] for this version)   https://doi.org/10.48550/arXiv.2603.24774 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Journal reference: IEEE Computer Magazine, Software Engineering Column, September 2026 Related DOI: https://doi.org/10.1109/MC.2026.3671990 Focus to learn more DOI(s) linking to related resources Submission history From: Valerio Terragni [view email] [v1] Wed, 25 Mar 2026 19:45:23 UTC (153 KB) Full-text links: Access Paper: View a PDF of the paper titled From Untestable to Testable: Metamorphic Testing in the Age of LLMs, by Valerio TerragniView PDF view license Current browse context: cs.SE < prev   |   next > new | recent | 2026-0...