发表机构
University of Sannio（萨尼奥大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本论文针对AI密集型网络物理系统（AI-CPS）的特殊技术债务，通过分析生态系统、代码仓库及开发者访谈刻画其特征，提出识别与缓解方法，并计划开发自动化工具以监控和偿还该类技术债务。
AI 中文摘要
人工智能（AI）组件正日益普及于多种软件系统，包括网络物理系统（CPS）。AI-CPS应用于自主车辆、工业、家庭自动化、机器人及医疗保健等多个领域，由硬件、AI组件和传统模块构成，其技术债务（TD）具有特殊性，可能比传统系统的技术债务更具挑战性。本论文旨在刻画AI-CPS的技术债务，并提出识别与修复方法。第一阶段，我们通过分析AI生态系统、AI-CPS代码仓库以及访谈开发者来刻画AI-CPS的技术债务。基于所获知识，我们定义了识别与缓解此类技术债务的方法。最后，我们计划开发并验证一款自动化工具，该工具支持智能体AI解决方案，以监控、管控并偿还AI-CPS的技术债务。
英文摘要
Artificial Intelligence (AI) components are increasingly pervasive in several software systems, including Cyber-Physical Systems (CPSs). AI-CPS are used in several domains, including autonomous vehicles, industry, home automation, robotics, and healthcare. Being composed of hardware, AI components, and conventional modules, AI-CPS can exhibit technical debt (TD) that is peculiar and potentially more challenging than that of conventional systems. This thesis aims to characterize AI-CPS TD and propose approaches for its identification and repair. In a first phase, we characterize AI-CPS TD by analyzing AI ecosystems and AI-CPS repositories, as well as interviewing developers. Based on the acquired knowledge, we define approaches to identify and mitigate such TD. Finally, we plan to develop and validate an automated tool that supports agentic AI solutions to monitor, govern, and repay AI-CPS TD.
CommentsDoctoral Symposium of the 41st IEEE/ACM International Conference on Automated Software Engineering (ASE 2026)
