The Vibe Shift in Software Engineering: Evaluating AI-Led Conversational Programming for Performance, Cognition, and Responsible Adoption

📄 arXiv: 2609.09560v1 📥 PDF

作者: Sales G. Aribe, Louie Jay S. Labastida

分类: cs.SE, cs.AI, cs.ET

发布日期: 2026-09-09

备注: 14 pages, 4 figures, 5 tables, Published by International Journal on Advanced Science, Engineering and Information Technology (IJASEIT)

期刊: S. Aribe & L. J. Labastida, The Vibe Shift in Software Engineering: Evaluating AI-Led Conversational Programming for Performance, Cognition, & Responsible Adoption, Int. J. Adv. Sci. Eng. Inf. Technol., vol. 16, no. 4, pp. 1459-1472, 2026

DOI: 10.18517/ijaseit.16.4.21812

💡 一句话要点

提出Vibe编码以提升软件开发效率与责任采用

🎯 匹配领域: 支柱九：具身大模型 (Embodied Foundation Models)

关键词: 对话式编程 人工智能 软件开发 认知负担 安全性 可维护性 责任采用

📋 核心要点

  1. 现有编程方法在效率与软件质量之间存在权衡，尤其在安全性和可维护性方面的挑战。
  2. Vibe编码通过自然语言与AI模型的互动，旨在提升开发效率，同时关注责任采用与认知影响。
  3. 实验结果表明，Vibe编码在任务完成时间上显著提升，但也带来了安全风险和可维护性问题。

📝 摘要（中文）

本研究评估了Vibe编码，这是一种新兴的AI主导对话式编程范式，允许开发者通过与大型语言模型的自然语言互动生成软件。采用混合方法设计，研究比较了Vibe编码与传统及AI辅助编码环境在性能效率、认知影响和责任采用方面的表现。结果显示，Vibe编码显著提高了开发效率，任务完成时间比传统编码减少27%，比AI辅助编码减少12%。然而，这些效率提升伴随着可维护性指数降低和安全漏洞增加，表明软件质量存在权衡。研究还提出了一个三支柱框架，强调人类与AI能力的混合整合、人类监督与透明问责，以及情境感知的部署。

🔬 方法详解

问题定义：本研究旨在解决传统编程方法在效率和软件质量方面的不足，尤其是安全性和可维护性的问题。现有方法往往在提升开发速度的同时，导致软件质量下降。

核心思路：Vibe编码通过与大型语言模型的自然语言交互，允许开发者以对话方式生成代码，从而减少语法负担并提高开发效率。该设计旨在结合人类的创造力与AI的计算能力。

技术框架：研究采用混合方法设计，包含定量与定性分析。实验分为三种条件：传统编码、AI辅助编码和Vibe编码，参与者在相同任务下进行比较。

关键创新：Vibe编码的核心创新在于其对话式编程方式，显著降低了开发者的语法负担，同时引入了新的认知挑战，特别是在信任与控制方面。

关键设计：研究中使用了描述性统计和重复测量ANOVA进行定量分析，定性数据通过主题分析进行处理。关键参数包括任务完成时间、可维护性指数和安全漏洞评估。

🖼️ 关键图片

img_0
img_1
img_2

📊 实验亮点

实验结果显示，Vibe编码在任务完成时间上比传统编码减少27%，比AI辅助编码减少12%。尽管效率提升显著，但可维护性指数降低和安全漏洞增加，提示在追求效率的同时需关注软件质量。

🎯 应用场景

Vibe编码的潜在应用领域包括软件开发、教育和AI辅助编程工具。其提高开发效率的能力使其在快速迭代和原型设计中具有实际价值，同时也为开发者提供了新的学习方式。未来，随着技术的成熟，Vibe编码可能会在更广泛的开发环境中得到应用。

📄 摘要（原文）

This study evaluates Vibe Coding, an emerging AI-led conversational programming paradigm that enables developers to generate software through natural-language interaction with large language models. Using a mixed-methods design, the study assessed performance efficiency, cognitive implications, and responsible adoption in comparison with traditional and AI-assisted coding environments. Thirty participants, including professional developers and advanced computing students, completed equivalent programming tasks under three experimental conditions. Quantitative data were analyzed using descriptive statistics and repeated-measures ANOVA, while qualitative data were examined through thematic analysis. Results show that vibe coding significantly improved development efficiency, reducing task completion time by 27% compared with traditional coding and 12% compared with AI-assisted coding. However, these gains were accompanied by lower maintainability indices and higher security vulnerabilities, indicating trade-offs in software quality. Usability results yielded a good rating (SUS = 71.4), while cognitive workload remained moderate (NASA-TLX = 55.5), reflecting reduced syntactic effort but increased linguistic reasoning. Thematic analysis identified trust calibration, loss of control, cognitive adaptation, and prompt-engineering strategy as key constructs. Notably, perceived loss of control was associated with increased security risks due to reduced transparency and validation of AI-generated outputs. Based on these findings, the study proposes a three-pillar framework for responsible adoption: hybrid integration of human and AI capabilities, human oversight and transparent accountability, and context-aware deployment. Overall, vibe coding enhances productivity but requires critical oversight, reinforcing its role as a transformative yet transitional paradigm in software development.