Generative artificial intelligence (GenAI) has taken software engineering by storm, as large language models (LLMs) have quickly come to generate large volumes of human-like text and code. Recent work has shown that, although excellent at mimicking human writing, these models have challenging limitations when writing code. Authors have identified how the code generated can be longer, more complex, worse performing, and contain more serious vulnerabilities than that written by humans. As the use of GenAI now shifts from a bleeding edge novelty to an amenity consolidated as the new status quo for software engineering, a pressing concern arises: It is still unclear how AI-written code impacts the long-term maintenance and evolution of software codebases. This PhD project investigates the previous concern by studying how AI-written code impacts four key qualities of source code: the system's ability to fulfill functional and non-functional requirements, the architectural cohesion, and the comprehensibility of the source code. By interacting with practitioners, analyzing software repositories, and proposing new approaches to using LLMs for software engineering, we expect to develop the theory and basis necessary to balance the benefits in productivity from GenAI with the everpressing needs for long-term software maintenance and evolution.

Development teams for mobile applications can receive thousands of user reviews daily. At the same time, these developers use different communication channels, such as the GitHub issue tracker. Although GitHub issues are accessible and manageable for developers, their content often differs starkly from what users write in app reviews. Issues may lack steps to reproduce bugs or insights that justify the priority of new feature requests. The sheer volume of user reviews for a popular app, combined with their heterogeneity and varying quality, makes manual integration into issue trackers unfeasible. We present an approach that automatically augments GitHub issues with informative user reviews to bridge the gap between user feedback and developer-managed issues. Using a state-of-the-art large language model (LLM), our approach automatically retrieves user reviews with high semantic textual similarity (STS) to the issue content and suggests reviews that augment developers' understanding of the issue. In this paper, we present large-scale quantitative and qualitative analyses to assess the feasibility of enriching development workflows with user-written information. Using over 37,000 issues and 750,000 reviews from 19 popular Free/Libre/Open Source Software (FLOSS) mobile applications, our approach augments 3,017(8%) issues with 7,287 (1%) potentially informative reviews. In addition to providing insights into user-reported bugs and feature requests, the information from these matches points toward a novel and promising way to leverage user reviews for concerted app evolution.

With its remarkably extensive code base, uniquely long lifespan, and undeniable importance to modern society, the Linux kernel is trivially hard to maintain. However, its decentralized development spread over many git trees and mailing lists makes empirically assessing the health of its maintainership model nothing short of a challenge. Off-the-shelf data analysis tools fail to capture crucial nuances exclusive to the kernel development model, such as the current authors who take part in every patch submitted, or how the commit flow between trees changes as new release candidates are created for every merge and stabilization window. We propose the Dashboard for Unified Kernel Statistics (DUKS), an innovative framework that supports multiple visualizations and data analyses previously unsupported for the Linux kernel. Using the Linux kernel mainline as an example, we demonstrate how DUKS could provide valuable insights for understanding the health of the kernel maintainership model. By coupling information from the kernel git trees collected from the Software Heritage repository alongside authorship information shared in mailing lists, we envision DUKS as a cornerstone open-access utility to support analyses on the Linux kernel evolution and maintenance. DUKS demo video: https://youtu.be/2RvUgzdr1fo