Revisiting the Impact of Pursuing Modularity for Code Generation
This challenges conventional software engineering practices for developers using AI code generation tools, though it is incremental in scope.
The study investigated whether modular programming improves code generation by large language models, finding that modularity does not significantly enhance performance, contrary to traditional expectations.
Modular programming, which aims to construct the final program by integrating smaller, independent building blocks, has been regarded as a desirable practice in software development. However, with the rise of recent code generation agents built upon large language models (LLMs), a question emerges: is this traditional practice equally effective for these new tools? In this work, we assess the impact of modularity in code generation by introducing a novel metric for its quantitative measurement. Surprisingly, unlike conventional wisdom on the topic, we find that modularity is not a core factor for improving the performance of code generation models. We also explore potential explanations for why LLMs do not exhibit a preference for modular code compared to non-modular code.