In CAS adaptation, a challenge is to define the dynamic architecture of the system and changes in its behavior. Implementation-wise, this is projected into an adaptation mechanism, typically realized as an Adaptation Manager (AM). With the advances of generative LLMs, generating AM code based on system specification and desired AM behavior (partially in natural language) is a tempting opportunity. The recent introduction of vibe coding suggests a way to target the problem of the correctness of generated code by iterative testing and vibe coding feedback loops instead of direct code inspection.
In this paper, we show that generating an AM via vibe coding feedback loops is a viable option when the verification of the generated AM is based on a very precise formulation of the functional requirements. We specify these as constraints in a novel temporal logic FCL that allows us to express the behavior of traces with much finer granularity than classical LTL enables.
Furthermore, we show that by combining the adaptation and vibe coding feedback loops where the FCL constraints are evaluated for the current system state, we achieved good results in the experiments with generating AMs for two example systems from the CAS domain. Typically, just a few feedback loop iterations were necessary, each feeding the LLM with reports describing detailed violations of the constraints. This AM testing was combined with high run path coverage achieved by different initial settings.
A Survey of Vibe Coding with Large Language Models
Institute of Computing Technology Chinese Academy of Sciences(中国科学院计算技术研究所);Duke University(杜克大学);University of California Merced(加州大学默塞德分校);Peking University(北京大学);University of Queensland(昆士兰大学)
Academic Vibe Coding: Opportunities for Accelerating Research in an Era of Resource Constraint
Massachusetts Eye & Ear(麻省眼耳医院);Harvard Medical School(哈佛医学院);Beth Israel Deaconess Medical Center(贝斯以色列女执事医疗中心);Massachusetts Institute of Technology(麻省理工学院);Harvard T.H. Chan School of Public Health(哈佛大学陈曾熙公共卫生学院)
Vibe Medicine: Redefining Biomedical Research Through Human-AI Co-Work
School of Computing, University of Georgia(佐治亚大学计算学院);Department of Biomedical Engineering, New Jersey Institute of Technology(新泽西理工学院生物医学工程系);Department of Computer Science and Engineering, University of Texas at Arlington(德克萨斯大学阿灵顿分校计算机科学与工程系)
SLEAN: Simple Lightweight Ensemble Analysis Network for Multi-Provider LLM Coordination: Design, Implementation, and Vibe Coding Bug Investigation Case Study
Why Human Guidance Matters in Collaborative Vibe Coding
Cornell University(康奈尔大学);Princeton University(普林斯顿大学);Massachusetts Institute of Technology(麻省理工学院);University of Cambridge(剑桥大学);New York University(纽约大学)
Vibe Coding in Product Teams: Reconfiguring AI-Assisted Workflows, Prototyping, and Collaboration
Netherlands and MIT Media Lab(荷兰和MIT媒体实验室);Notion Labs(Notion实验室);Collov AI;Cornell University(康奈尔大学);Goizueta Business School, Emory University(埃默里大学戈伊兹埃塔商学院);Centrum Wiskunde & Informatica, The Netherlands and Utrecht University, The Netherlands(荷兰代尔夫特理工大学和乌得勒支大学)
Unpacking Vibe Coding: Help-Seeking Processes in Student-AI Interactions While Programming
CATALPA;FernUniversität in Hagen(费尔恩大学);School of Computing and Information Systems(计算与信息系统学院);University of Melbourne(墨尔本大学);School of Computing(计算学院);University of Eastern Finland(东芬兰大学)
Coding With AI: From a Reflection on Industrial Practices to Future Computer Science and Software Engineering Education
R. B. Annis School of Engineering(R. B. Annis 工程学院);University of Indianapolis(印第安纳大学);E. S. Witchger School of Engineering(E. S. Witchger 工程学院);Marian University(玛丽安大学);University of Maryland Eastern Shore(马里兰大学东部分校);The Boehm Center for Systems and Software Engineering(Boehm 系统与软件工程中心)
Last Secure Code Benchmark: Is the Code You Vibe Secure?
National University of Singapore(新加坡国立大学);Qwen Team, Alibaba Token Hub, Alibaba Group(阿里通义千问团队、阿里Token Hub、阿里巴巴集团);Cloud Safety and Security, Alibaba Cloud, Alibaba Group(阿里云云安全与安全部门、阿里云、阿里巴巴集团)
本研究推出 Last Secure Code Benchmark 评估编码智能体的安全代码生成,发现前沿智能体生成的代码功能通过率高但安全通过率低,vibe 编码生成代码的安全性存在严重隐患。
From Idea to Classroom in Days: Using "Vibe Coding" to Create a Programming Process Visualizer from IDE Activity Logs
Institute of Computer Science University of Tartu Tartu, Estonia ORCID: 0000-0002-2638-7253;Institute of Computer Science University of Tartu Tartu, Estonia ORCID: 0000-0003-3303-5245
Dr. Claw: An AI Scientist Workspace for Vibe Research
Lehigh University(利哈伊大学);University of Illinois Chicago(伊利诺伊大学芝加哥分校);University of Pennsylvania(宾夕法尼亚大学);University of Maryland(马里兰大学);University of Notre Dame(圣母大学);University of British Columbia(不列颠哥伦比亚大学)
Beyond the 'Diff': Addressing Agentic Entropy in Agentic Software Development
Dipartimento Tecnologie Innovative, SUPSI(技术创新部,SUPSI);Dalle Molle Institute for Artificial Intelligence (IDSIA), SUPSI(达勒莫利人工智能研究所(IDSIA),SUPSI);Management in Networked and Digital Societies (MINDS) Department, Kozminski University(网络化与数字化社会管理(MINDS)系,科津斯基大学);Institute of Biomedical Ethics and History of Medicine, University of Zurich(生物医学伦理与医学史研究所,苏黎世大学);ETH Zurich(苏黎世联邦理工学院)
Assisted morbidity coding: the SISCO.web use case for identifying the main diagnosis in Hospital Discharge Records
Institute of Informatics and Telematics, National Research Council(国家研究委员会信息学与电信研究所);Azienda Sanitaria Universitaria Giuliano Isontina (ASUGI)(朱利亚诺-伊松蒂纳大学卫生集团(ASUGI))
针对临床编码可重复性差的问题,本文提出 SISCO.web 方法,利用 NLP 算法、特定编码规则和 ad hoc 决策树,辅助医生使用 ICD 在住院出院记录中识别主要病理状况并提供准确的编码建议。