Do AI Agents Write Less Maintainable Code Than Human Developers?

Betty Li Hou, Shaswat P Patel, Arun Purohit, Kai Xu, Jane Pan, He He, Valerie Chen

Keywords: coding agents, large language models, maintainability, evaluation, software engineering

TL;DR: Agent-authored code can solve the immediate task but is often less maintainable than human-written code, leading to lower downstream task success and greater code quality degradation when future agents build on it.

Abstract: Coding agents offer major efficiency gains for software engineering, but their effects on the downstream functionality and quality of a code base remain understudied. Existing evaluations largely focus on whether agents can resolve individual issues, overlooking how agent-authored code may affect future development by making the code harder to interpret, extend, or build on---the code's \emph{maintainability}. We design a controlled experiment to compare the maintainability of agent-authored versus human-authored code by constructing two-step pull-request chains in which the same downstream task is performed on top of either human- or agent-authored code. We find that agent-authored code consistently leads to more downstream failures than human-authored code, with absolute task resolve rate drops of 1.0 to 13.0 percentage drop across Claude 4.5 Sonnet, GPT-5, GLM 4.7, and MiniMax 2.5, as well as larger increases across structural complexity and verbosity metrics. We report additional findings on differences in performance and code quality across task types and common failure modes. Our findings suggest that coding agents contribute to both downstream performance drops and code quality degradation, a critical consideration as agent use becomes more widespread and agent-authored code increasingly becomes the foundation for future development.

Track: Regular Paper (9 pages)

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 143