arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.18607cs.AI
收藏

基于反馈的自动验证在CAS适应中的Vibe编码实现

Feedback-based Automated Verification in Vibe Coding of CAS Adaptation Built on Constraint Logic

Michal Töpfer, František Plášil, Tomáš Bureš, Petr Hnětynka

AI总结:

本文提出通过Vibe编码反馈循环结合精确约束逻辑,实现CAS适应中AM的自动验证与生成,有效提升代码正确性与适应性能。

摘要:

在CAS适应中,一个挑战是定义系统的动态架构及其行为的变化。在实现层面,这被投影为一种适应机制,通常实现为适应管理器(AM)。随着生成式大语言模型(LLM)的发展,根据系统规范和期望的AM行为(部分以自然语言描述)生成AM代码成为一种有吸引力的机会。最近引入的Vibe编码方法提出了一种解决生成代码正确性问题的方法,即通过迭代测试和Vibe编码反馈循环而不是直接代码检查。在本文中,我们表明,当生成AM的验证基于对功能需求的非常精确的描述时,通过Vibe编码反馈循环生成AM是一种可行的方法。我们将这些描述指定为一种新的时序逻辑FCL中的约束,使我们能够以比经典LTL更细的粒度表达轨迹的行为。此外,我们还表明,通过将适应和Vibe编码反馈循环结合,其中FCL约束在当前系统状态下进行评估,我们在为两个CAS领域示例系统生成AMs的实验中取得了良好的结果。通常,只需很少的反馈循环迭代,每次都将LLM馈以描述约束违反细节的报告。这种AM测试结合了通过不同初始设置实现的高运行路径覆盖率。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑