对比三种AI辅助开发模式，发现更高自主性AI能提升效率与合规性。
Three-Phase Evaluation of AI-Assisted Software Development Life Cycle
- 分三阶段测试局部、全量AI辅助及AWS Kiro全栈工具链
- 最高自主性AI使开发耗时减少，需求符合率提升，认知负荷降低
- 尽管开发者略有不满，但整体表现最优，提示工具架构影响关键
本文探索了不同水平的AI自主性对软件开发效率、需求符合度和开发者认知负担的影响。四名开发者在三个连续阶段重写了同一全栈网页应用：部分使用GitHub Copilot的AI辅助开发、完全依赖GitHub Copilot的AI独占工作流，以及完全依赖AWS Kiro的AI独占工作流。评估指标包括开发投入（小时）、需求符合度（RITM分数）、AI交互效率和NASA-TLX工作负荷量表。结果显示，随着AI自主性提高，开发耗时减少，需求符合度提升，自我报告的认知负荷下降，开发者沮丧感轻微上升。其中，使用AWS Kiro的阶段在多数测量维度上表现最佳，表明工具架构可能独立于AI自主性水平影响最终效果。
原文摘要 · Abstract (English)
This paper presents an exploratory evaluation of how increasing levels of AI autonomy affect software development productivity, requirement adherence, and developer cognitive workload. A team of four developers reimplemented the same full-stack web application across three sequential phases: partial AI-assisted development using GitHub Copilot, an AI-exclusive workflow using GitHub Copilot, and an AI-exclusive workflow using AWS Kiro. Evaluation metrics included development effort (hours), requirement adherence (RITM score), AI-interaction efficiency, and NASA-TLX workload measures. Across phases, higher levels of AI autonomy were associated with reduced development effort, improved requirement adherence, and lower self-reported mental workload, while developer frustration increased modestly. The AWS Kiro phase achieved the strongest overall performance on most measured dimensions, suggesting that tooling architecture may influence outcomes independently of AI autonomy level.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。