Logan Murphy, Wilson Sy, Rhys Balevicius, Kelsie Fung, Karenna Kung, Aren A. Babikian, Marsha Chećhik · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.29758 · cited by 0 works (OpenAlex) · open-access PDF
El uso de herramientas basadas en la IA en el desarrollo de software está cambiando rápidamente la forma en que se produce el software, lo que permite generar grandes volúmenes de código con un esfuerzo humano limitado. Sin embargo, esto plantea desafíos fundamentales para garantizar que los artefactos generados estén alineados con la intención del desarrollador y hayan sido adecuadamente validados. En este trabajo, proponemos el uso de argumentación estructurada para impulsar el desarrollo de software asistido por IA. Inspirados por las técnicas de ingeniería de seguridad para sistemas críticos a la seguridad, definimos un lenguaje de razonamientos de justificación que relacionan explícitamente con las promesas de lenguaje natural informales, las especificaciones formales, las suposiciones sobre las intenciones del desarrollador y las pruebas de análisis de programas en un formato estruct
Machine translation (Meta M2M100); the English original follows.
The use of AI-based tools in software development is rapidly changing how software is produced, enabling large volumes of code to be generated with limited human implementation effort. However, this raises fundamental challenges for ensuring that generated artifacts are aligned with developer intent and have been appropriately validated. In this work, we propose the use of structured argumentation in driving AI-assisted software development. Inspired by techniques from assurance engineering for safety-critical systems, we define a language of justification rationales that explicitly relate informal natural language prompts, formal specifications, assumptions about developer intentions, and program analysis evidence in a structured and verifiable format. We then describe AssureCode, a tool-supported methodology for creating such rationales as part of agentic code generation. We provide an empirical analysis of our implementation where we investigate its capacity to contribute towards justified assurance of correctness for AI-generated code.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Computer science, Verifiable secret sharing, Correctness, Argumentation theory, Software engineering, Trustworthiness
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29758, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange