arXiv subjects

Shamse Tasnim Cynthia

Publications and source records attributed to Shamse Tasnim Cynthia.

9 recordsLinked to original sources

arXiv2026

"Go Home Copilot, You're Drunk": Understanding Developer Responses to Agent-Generated Code Review Comments

Code review is a critical quality assurance practice in software engineering development, and AI coding agents are increasingly generating review comments on pull requests. However, little is known about how developers actually respond to such agent-generated feedback. In this paper, we present the first large-scale empirical study on the resolution of agent-generated code review comments. We analyze $54{,}791$ comments generated by five widely used coding agents (i.e., Copilot, Cursor, Codex, Devin, and Claude) across $342$ Python repositories on GitHub. We examine (1) resolution rates across agents and comment types, (2) the role of developer experience, and (3) characteristics that influence comment usefulness. Our results show that resolution rate varies considerably across agents, with Copilot accounting for the majority of resolved comments (72.9\%). Core developers resolve the majority of agent-generated feedback, particularly for \textit{design} and \textit{evolvability}-related comments, while peripheral developers are more involved in resolving \textit{functional defect} comments. Through open card sorting of 470 unresolved comment discussions, we identify \textit{ten} discussion patterns explaining why comments remain unresolved, with \textit{incorrect suggestions} and \textit{intentional design decisions} being the most prevalent. Finally, our analysis reveals that the presence of an inline \textit{code suggestion} is the strongest predictor of comment resolution, while lengthy and complex comments are less likely to be acted upon. Our findings provide insights for improving AI-generated code review feedback and its integration into development workflows.

cs.SE↗

arXiv2026

From Generic to Personalized: Exploring Persona-Aware Code Review Explanations

Code review is essential for ensuring software quality and supporting collaboration, yet prior work shows that developers can interpret code review comments differently. These differences can hinder effective communication, particularly in collaborative settings. To address this challenge, we explore the potential of personified code review explanations. We report initial findings from an ongoing mixed-methods user study in which developers evaluated persona-aligned review comments across multiple code snippets. Our results suggest that preferences for explanation styles vary across problem-solving styles, experience levels, and roles. Across problem-solving style profiles, developers valued explanatory depth, learning support, practical suggestions, and risk awareness over conciseness, highlighting the need to balance personalization with clarity and trust. Based on these findings, we outline a vision for inclusive, human-centered AI-assisted code review systems that adapt feedback to developers' problem-solving preferences.

cs.SE↗

arXiv2026

Are We All Using Agents the Same Way? An Empirical Study of Core and Peripheral Developers Use of Coding Agents

Autonomous AI agents are transforming software development and redefining how developers collaborate with AI. Prior research shows that the adoption and use of AI-powered tools differ between core and peripheral developers. However, it remains unclear how this dynamic unfolds in the emerging era of autonomous coding agents. In this paper, we present the first empirical study of 9,427 agentic PRs, examining how core and peripheral developers use, review, modify, and verify agent-generated contributions prior to acceptance. Through a mix of qualitative and quantitative analysis, we make four key contributions. First, a subset of peripheral developers use agents more often, delegating tasks evenly across bug fixing, feature addition, documentation, and testing. In contrast, core developers focus more on documentation and testing, yet their agentic PRs are frequently merged into the main/master branch. Second, core developers engage slightly more in review discussions than peripheral developers, and both groups focus on evolvability issues. Third, agentic PRs are less likely to be modified, but when they are, both groups commonly perform refactoring. Finally, peripheral developers are more likely to merge without running CI checks, whereas core developers more consistently require passing verification before acceptance. Our analysis offers a comprehensive view of how developer experience shapes integration offer insights for both peripheral and core developers on how to effectively collaborate with coding agents.

cs.SE↗

arXiv2026

Beyond Bug Fixes: An Empirical Investigation of Post-Merge Code Quality Issues in Agent-Generated Pull Requests

The increasing adoption of AI coding agents has increased the number of agent-generated pull requests (PRs) merged with little or no human intervention. Although such PRs promise productivity gains, their post-merge code quality remains underexplored, as prior work has largely relied on benchmarks and controlled tasks rather than large-scale post-merge analyses. To address this gap, we analyze 1,210 merged agent-generated bug-fix PRs from Python repositories in the AIDev dataset. Using SonarQube, we perform a differential analysis between base and merged commits to identify code quality issues newly introduced by PR changes. We examine issue frequency, density, severity, and rule-level prevalence across five agents. Our results show that apparent differences in raw issue counts across agents largely disappear after normalizing by code churn, indicating that higher issue counts are primarily driven by larger PRs. Across all agents, code smells dominate, particularly at critical and major severities, while bugs are less frequent but often severe. Overall, our findings show that merge success does not reliably reflect post-merge code quality, highlighting the need for systematic quality checks for agent-generated bug-fix PRs.

cs.SE↗

arXiv2025

Towards LLM-Powered Task-Aware Retrieval of Scientific Workflows for Galaxy

Scientific Workflow Management Systems (SWfMSs) such as Galaxy have become essential infrastructure in bioinformatics, supporting the design, execution, and sharing of complex multi-step analyses. Despite hosting hundreds of reusable workflows across domains, Galaxy's current keyword-based retrieval system offers limited support for semantic query interpretation and often fails to surface relevant workflows when exact term matches are absent. To address this gap, we propose a task-aware, two-stage retrieval framework that integrates dense vector search with large language model (LLM)-based reranking. Our system first retrieves candidate workflows using state-of-the-art embedding models and then reranks them using instruction-tuned generative LLMs (GPT-4o, Mistral-7B) based on semantic task alignment. To support robust evaluation, we construct a benchmark dataset of Galaxy workflows annotated with semantic topics via BERTopic and synthesize realistic task-oriented queries using LLMs. We conduct a comprehensive comparison of lexical, dense, and reranking models using standard IR metrics, presenting the first systematic evaluation of retrieval performance in the Galaxy ecosystem. Results show that our approach significantly improves top-k accuracy and relevance, particularly for long or under-specified queries. We further integrate our system as a prototype tool within Galaxy, providing a proof-of-concept for LLM-enhanced workflow search. This work advances the usability and accessibility of scientific workflows, especially for novice users and interdisciplinary researchers.

cs.SE↗

arXiv2025

How Do Community Smells Influence Self-Admitted Technical Debt in Machine Learning Projects?

Community smells reflect poor organizational practices that often lead to socio-technical issues and the accumulation of Self-Admitted Technical Debt (SATD). While prior studies have explored these problems in general software systems, their interplay in machine learning (ML)-based projects remains largely underexamined. In this study, we investigated the prevalence of community smells and their relationship with SATD in open-source ML projects, analyzing data at the release level. First, we examined the prevalence of ten community smell types across the releases of 155 ML-based systems and found that community smells are widespread, exhibiting distinct distribution patterns across small, medium, and large projects. Second, we detected SATD at the release level and applied statistical analysis to examine its correlation with community smells. Our results showed that certain smells, such as Radio Silence and Organizational Silos, are strongly correlated with higher SATD occurrences. Third, we considered the six identified types of SATD to determine which community smells are most associated with each debt category. Our analysis revealed authority- and communication-related smells often co-occur with persistent code and design debt. Finally, we analyzed how the community smells and SATD evolve over the releases, uncovering project size-dependent trends and shared trajectories. Our findings emphasize the importance of early detection and mitigation of socio-technical issues to maintain the long-term quality and sustainability of ML-based systems.

cs.SE↗

arXiv2025

Gender Disparities in Contributions, Leadership, and Collaboration: An Exploratory Study on Software Systems Research

Gender diversity enhances research by bringing diverse perspectives and innovative approaches. It ensures equitable solutions that address the needs of diverse populations. However, gender disparity persists in research where women remain underrepresented, which might limit diversity and innovation. Many even leave scientific careers as their contributions often go unnoticed and undervalued. Therefore, understanding gender-based contributions and collaboration dynamics is crucial to addressing this gap and creating a more inclusive research environment. In this study, we analyzed 2,000 articles published over the past decade in the Journal of Systems and Software (JSS). From these, we selected 384 articles that detailed authors' contributions and contained both female and male authors to investigate gender-based contributions. Our contributions are fourfold. First, we analyzed women's engagement in software systems research. Our analysis showed that only 32.74% of the total authors are women and female-led or supervised studies were fewer than those of men. Second, we investigated female authors' contributions across 14 major roles. Interestingly, we found that women contributed comparably to men in most roles, with more contributions in conceptualization, writing, and reviewing articles. Third, we explored the areas of software systems research and found that female authors are more actively involved in human-centric research domains. Finally, we analyzed gender-based collaboration dynamics. Our findings revealed that female supervisors tended to collaborate locally more often than national-level collaborations. Our study highlights that females' contributions to software systems research are comparable to those of men. Therefore, the barriers need to be addressed to enhance female participation and ensure equity and inclusivity in research.

cs.SE↗

arXiv2025

Identification and Optimization of Redundant Code Using Large Language Models

Redundant code is a persistent challenge in software development that makes systems harder to maintain, scale, and update. It adds unnecessary complexity, hinders bug fixes, and increases technical debt. Despite their impact, removing redundant code manually is risky and error-prone, often introducing new bugs or missing dependencies. While studies highlight the prevalence and negative impact of redundant code, little focus has been given to Artificial Intelligence (AI) system codebases and the common patterns that cause redundancy. Additionally, the reasons behind developers unintentionally introducing redundant code remain largely unexplored. This research addresses these gaps by leveraging large language models (LLMs) to automatically detect and optimize redundant code in AI projects. Our research aims to identify recurring patterns of redundancy and analyze their underlying causes, such as outdated practices or insufficient awareness of best coding principles. Additionally, we plan to propose an LLM agent that will facilitate the detection and refactoring of redundancies on a large scale while preserving original functionality. This work advances the application of AI in identifying and optimizing redundant code, ultimately helping developers maintain cleaner, more readable, and scalable codebases.

cs.SE↗

arXiv2025

An Empirical Study on the Impact of Gender Diversity on Code Quality in AI Systems

The rapid advancement of AI systems necessitates high-quality, sustainable code to ensure reliability and mitigate risks such as bias and technical debt. However, the underrepresentation of women in software engineering raises concerns about homogeneity in AI development. Studying gender diversity in AI systems is crucial, as diverse perspectives are essential for improving system robustness, reducing bias, and enhancing overall code quality. While prior research has demonstrated the benefits of diversity in general software teams, its specific impact on the code quality of AI systems remains unexplored. This study addresses this gap by examining how gender diversity within AI teams influences project popularity, code quality, and individual contributions. Our study makes three key contributions. First, we analyzed the relationship between team diversity and repository popularity, revealing that diverse AI repositories not only differ significantly from non-diverse ones but also achieve higher popularity and greater community engagement. Second, we explored the effect of diversity on the overall code quality of AI systems and found that diverse repositories tend to have superior code quality compared to non-diverse ones. Finally, our analysis of individual contributions revealed that although female contributors contribute to a smaller proportion of the total code, their contributions demonstrate consistently higher quality than those of their male counterparts. These findings highlight the need to remove barriers to female participation in AI development, as greater diversity can improve the overall quality of AI systems.

cs.SE↗