一句话：系统审计 AI 生成软件的技术债，揭示机器签名缺陷、推理-复杂度权衡与体积-质量反比律。
论文指出，LLM 在自动软件工程中的承诺常以功能正确性衡量，却忽视了长期可维护性。作者对 AI 生成软件中的技术债进行系统审计，分析范围覆盖单文件算法任务与复杂自主代理生成的系统。研究发现，AI 并未消除缺陷，而是引入了一种独特的“机器签名”缺陷，并识别出推理-复杂度权衡：模型能力越强，生成的代码越臃肿、耦合越严重。这种架构退化非常显著，作者据此提出“体积-质量反比律”，即代码体积几乎可以完美预测结构退化。关键的是，功能正确性和详细提示都无法缓解这种退化。论文由此主张，AI 软件工程的核心问题应从代码生成转向架构复杂度管理，未来需让代理具备显式的架构远见，以确保软件不仅功能正确，而且可维护。
The promise of Large Language Models (LLMs) in automated software engineering is often measured by functional correctness, overlooking the critical issue of long-term maintainability. This paper presents a systematic audit of technical debt in AI-generated software, revealing that AI does not eliminate flaws but rather introduces a distinct "machine signature" of defects. Our multi-scale analysis—spanning single-file algorithmic tasks and complex, agent-generated systems—identifies a fundamental Reasoning-Complexity Trade-off: as models become more capable, they generate increasingly bloated and coupled code. This architectural decay is so pronounced that we establish a Volume-Quality Inverse Law, where code volume is a near-perfect predictor of structural degradation. Crucially, we demonstrate that neither functional correctness nor detailed prompting mitigates this decay. These findings challenge the current paradigm of prompt-driven generation, reframing the central problem of AI-based software engineering from one of code generation to one of architectural complexity management. We conclude that future progress depends on equipping agents with explicit architectural foresight to ensure the software they build is not just functional, but also maintainable.