Searcharxiv⌕ Search

arXiv subjects

Eray Tüzün

Publications and source records attributed to Eray Tüzün.

32 records · Page 2Linked to original sources

Agents in the Sandbox: End-to-End Crash Bug Reproduction for Minecraft

Reproducing game bugs, particularly crash bugs in continuously evolving games like Minecraft, is a notoriously manual, time-consuming, and challenging process to automate; insights from a key decision maker from Minecraft we interviewed confirm this, highlighting that a substantial portion of crash reports necessitate manual scenario reconstruction. Despite the success of LLM-driven bug reproduction in other software domains, games, with their complex interactive environments, remain largely unaddressed. This paper introduces BugCraft, a novel end-to-end framework designed to automate the reproduction of crash bugs in Minecraft directly from user-submitted bug reports, addressing the critical gap in automated game bug reproduction. BugCraft employs a two-stage approach: first, a Step Synthesizer leverages LLMs and Minecraft Wiki knowledge to transform bug reports into high-quality, structured steps to reproduce (S2R). Second, an Action Model, powered by a vision-based LLM agent and a custom macro API, executes these S2R steps within Minecraft to trigger the reported crash. To facilitate evaluation, we introduce BugCraft-Bench, a curated dataset of Minecraft crash bug reports. On BugCraft-Bench, our framework end-to-end reproduced 34.9% of crash bugs with GPT-4.1, outperforming baseline computer-use models by 37%. BugCraft demonstrates the feasibility of automated reproduction of crash bugs in complex game environments using LLMs, opening promising avenues for game testing and development. Finally, we make our code open at https://bugcraft2025.github.io

cs.SE↗

Towards Automated Detection of Inline Code Comment Smells

Code comments are important in software development because they directly influence software maintainability and overall quality. Bad practices of code comments lead to code comment smells, negatively impacting software maintenance. Recent research has been conducted on classifying inline code comment smells, yet automatically detecting these still remains a challenge. We aim to automatically detect and classify inline code comment smells through machine learning (ML) models and a large language model (LLM) to determine how accurately each smell type can be detected. We enhanced a previously labeled dataset, where comments are labeled according to a determined taxonomy, by augmenting it with additional code segments and their associated comments. GPT 4, a large language model, was used to classify code comment smells on both the original and augmented datasets to evaluate its performance. In parallel, we trained and tested seven different machine learning algorithms on the augmented dataset to compare their classification performance against GPT 4. The performance of models, particularly Random Forest, which achieved an overall accuracy of 69 percent, along with Gradient Boosting and Logistic Regression, each achieving 66 percent and 65 percent, respectively, establishes a solid baseline for future research in this domain. The Random Forest model outperformed all other ML models, by achieving the highest Matthews Correlation Coefficient (MCC) score of 0.44. The augmented dataset improved the overall classification accuracy of the GPT 4 model predictions from 34 percent to 55 percent. This study contributes to software maintainability by exploring the automatic detection and classification of inline code comment smells. We have made our augmented dataset and code artifacts available online, offering a valuable resource for developing automated comment smell detection tools.

cs.SE↗

Evaluating Large Language Models for Code Review

Context: Code reviews are crucial for software quality. Recent AI advances have allowed large language models (LLMs) to review and fix code; now, there are tools that perform these reviews. However, their reliability and accuracy have not yet been systematically evaluated. Objective: This study compares different LLMs' performance in detecting code correctness and suggesting improvements. Method: We tested GPT4o and Gemini 2.0 Flash on 492 AI generated code blocks of varying correctness, along with 164 canonical code blocks from the HumanEval benchmark. To simulate the code review task objectively, we expected LLMs to assess code correctness and improve the code if needed. We ran experiments with different configurations and reported on the results. Results: With problem descriptions, GPT4o and Gemini 2.0 Flash correctly classified code correctness 68.50% and 63.89% of the time, respectively, and corrected the code 67.83% and 54.26% of the time for the 492 code blocks of varying correctness. Without problem descriptions, performance declined. The results for the 164 canonical code blocks differed, suggesting that performance depends on the type of code. Conclusion: LLM code reviews can help suggest improvements and assess correctness, but there is a risk of faulty outputs. We propose a process that involves humans, called the "Human in the loop LLM Code Review" to promote knowledge sharing while mitigating the risk of faulty outputs.

cs.SE↗

Evaluating the Impact of Data Cleaning on the Quality of Generated Pull Request Descriptions

Pull Requests (PRs) are central to collaborative coding, summarizing code changes for reviewers. However, many PR descriptions are incomplete, uninformative, or have out-of-context content, compromising developer workflows and hindering AI-based generation models trained on commit messages and original descriptions as "ground truth." This study examines the prevalence of "noisy" PRs and evaluates their impact on state-of-the-art description generation models. To do so, we propose four cleaning heuristics to filter noise from an initial dataset of 169K+ PRs drawn from 513 GitHub repositories. We train four models-BART, T5, PRSummarizer, and iTAPE-on both raw and cleaned datasets. Performance is measured via ROUGE-1, ROUGE-2, and ROUGE-L metrics, alongside a manual evaluation to assess description quality improvements from a human perspective. Cleaning the dataset yields significant gains: average F1 improvements of 8.6% (ROUGE-1), 8.7% (ROUGE-2), and 8.5% (ROUGE-L). Manual assessment confirms higher readability and relevance in descriptions generated by the best-performing model, BART when trained on cleaned data. Dataset refinement markedly enhances PR description generation, offering a foundation for more accurate AI-driven tools and guidelines to assist developers in crafting high-quality PR descriptions.

cs.SE↗

SmartDelta Methodology: Automated Quality Assurance and Optimization for Incremental System Engineering

Modern software systems undergo frequent updates, continuously evolving with new versions and variants to offer new features, improve functionality, and expand usability. Given the rapid pace of software evolution, organizations require effective tools and methods to mitigate the challenges associated with these changes, also called deltas. To address these challenges, the international SmartDelta Project joined industry and academia to develop and test solutions for incremental development and quality assurance. This paper provides insights into the SmartDelta project achievements and highlights one main contribution: the SmartDelta Methodology, a domain-unspecific concept for delta management in incremental software engineering. This methodology enables companies to identify gaps in their continuous engineering environment across six stages and helps to discover new tools in various technical areas. Additionally, the paper presents seven selected tools at different stages of the methodology.

cs.SE↗

Automated Code Review In Practice

Code review is a widespread practice to improve software quality and transfer knowledge. It is often seen as time-consuming due to the need for manual effort and potential delays. Several AI-assisted tools, such as Qodo, GitHub Copilot, and Coderabbit, provide automated reviews using large language models (LLMs). The effects of such tools in the industry are yet to be examined. This study examines the impact of LLM-based automated code review tools in an industrial setting. The study was conducted within a software development environment that adopted an AI-assisted review tool (based on open-source Qodo PR Agent). Around 238 practitioners across ten projects had access to the tool. We focused on three projects with 4,335 pull requests, 1,568 of which underwent automated reviews. Data collection comprised three sources: (1) a quantitative analysis of pull request data, including comment labels indicating whether developers acted on the automated comments, (2) surveys sent to developers regarding their experience with reviews on individual pull requests, and (3) a broader survey of 22 practitioners capturing their general opinions on automated reviews. 73.8% of automated comments were resolved. However, the average pull request closure duration increased from five hours 52 minutes to eight hours 20 minutes, with varying trends across projects. Most practitioners reported a minor improvement in code quality due to automated reviews. The LLM-based tool proved useful in software development, enhancing bug detection, increasing awareness of code quality, and promoting best practices. However, it also led to longer pull request closure times and introduced drawbacks like faulty reviews, unnecessary corrections, and irrelevant comments.

cs.SE↗

RefExpo: Unveiling Software Project Structures through Advanced Dependency Graph Extraction

The dependency graph (DG) of a software project offers valuable insights for identifying its key components and has been leveraged in numerous studies. However, there is a lack of reusable tools for DG extraction. Existing tools are either outdated and difficult to configure or fail to provide accurate analysis. This study introduces RefExpo, a reusable DG extraction tool that supports multiple languages such as Java, Python, and JavaScript. RefExpo is a plugin based on IntelliJ, a well-maintained and reputed IDE. We also compile an initial version of our dataset, consisting of 20 Java and Python projects. RefExpo's validity is evaluated at two levels: specific language features and comparisons against other tools, referred to as micro and macro levels. Our results show RefExpo achieves 92\% and 100\% recall on micro test suites Judge and PyCG for Python and Java, respectively. In macro-level experiments, RefExpo outperformed existing tools by 31\% and 7\% in finding unique and shared results. The installable version of RefExpo is available on the IntelliJ marketplace, and a short video describing its functionality is available on YouTube.

cs.SE↗

Bus Factor Explorer

Bus factor (BF) is a metric that tracks knowledge distribution in a project. It is the minimal number of engineers that have to leave for a project to stall. Despite the fact that there are several algorithms for calculating the bus factor, only a few tools allow easy calculation of bus factor and convenient analysis of results for projects hosted on Git-based providers. We introduce Bus Factor Explorer, a web application that provides an interface and an API to compute, export, and explore the Bus Factor metric via treemap visualization, simulation mode, and chart editor. It supports repositories hosted on GitHub and enables functionality to search repositories in the interface and process many repositories at the same time. Our tool allows users to identify the files and subsystems at risk of stalling in the event of developer turnover by analyzing the VCS history. The application and its source code are publicly available on GitHub at https://github.com/JetBrains-Research/bus-factor-explorer. The demonstration video can be found on YouTube: https://youtu.be/uIoV79N14z8

cs.SE↗

Evaluating the Code Quality of AI-Assisted Code Generation Tools: An Empirical Study on GitHub Copilot, Amazon CodeWhisperer, and ChatGPT

Context: AI-assisted code generation tools have become increasingly prevalent in software engineering, offering the ability to generate code from natural language prompts or partial code inputs. Notable examples of these tools include GitHub Copilot, Amazon CodeWhisperer, and OpenAI's ChatGPT. Objective: This study aims to compare the performance of these prominent code generation tools in terms of code quality metrics, such as Code Validity, Code Correctness, Code Security, Code Reliability, and Code Maintainability, to identify their strengths and shortcomings. Method: We assess the code generation capabilities of GitHub Copilot, Amazon CodeWhisperer, and ChatGPT using the benchmark HumanEval Dataset. The generated code is then evaluated based on the proposed code quality metrics. Results: Our analysis reveals that the latest versions of ChatGPT, GitHub Copilot, and Amazon CodeWhisperer generate correct code 65.2%, 46.3%, and 31.1% of the time, respectively. In comparison, the newer versions of GitHub CoPilot and Amazon CodeWhisperer showed improvement rates of 18% for GitHub Copilot and 7% for Amazon CodeWhisperer. The average technical debt, considering code smells, was found to be 8.9 minutes for ChatGPT, 9.1 minutes for GitHub Copilot, and 5.6 minutes for Amazon CodeWhisperer. Conclusions: This study highlights the strengths and weaknesses of some of the most popular code generation tools, providing valuable insights for practitioners. By comparing these generators, our results may assist practitioners in selecting the optimal tool for specific tasks, enhancing their decision-making process.

cs.SE↗

Investigating the Impact of Forgetting in Software Development

Context: Forgetting is defined as a gradual process of losing information. Even though there are many studies demonstrating the effect of forgetting in software development, to the best of our knowledge, no study explores the impact of forgetting in software development using a controlled experiment approach. Objective: We would like to provide insights on the impact of forgetting in software development projects. We want to examine whether the recency & frequency of interaction impact forgetting in software development. Methods: We will conduct an experiment that examines the impact of forgetting in software development. Participants will first do an initial task. According to their initial task performance, they will be assigned to either the experiment or the control group. The experiment group will then do two additional tasks to enhance their exposure to the code. Both groups will then do a final task to see if additional exposure to the code benefits the experiment group's performance in the final task. Finally, we will conduct a survey and a recall task with the same participants to collect data about their perceptions of forgetting and quantify their memory performance, respectively.

cs.SE↗

Bus Factor In Practice

Bus factor is a metric that identifies how resilient is the project to the sudden engineer turnover. It states the minimal number of engineers that have to be hit by a bus for a project to be stalled. Even though the metric is often discussed in the community, few studies consider its general relevance. Moreover, the existing tools for bus factor estimation focus solely on the data from version control systems, even though there exists other channels for knowledge generation and distribution. With a survey of 269 engineers, we find that the bus factor is perceived as an important problem in collective development, and determine the highest impact channels of knowledge generation and distribution in software development teams. We also propose a multimodal bus factor estimation algorithm that uses data on code reviews and meetings together with the VCS data. We test the algorithm on 13 projects developed at JetBrains and compared its results to the results of the state-of-the-art tool by Avelino et al. against the ground truth collected in a survey of the engineers working on these projects. Our algorithm is slightly better in terms of both predicting the bus factor as well as key developers compared to the results of Avelino et al. Finally, we use the interviews and the surveys to derive a set of best practices to address the bus factor issue and proposals for the possible bus factor assessment tool.

cs.SE↗

What Makes Agile Software Development Agile?

Together with many success stories, promises such as the increase in production speed and the improvement in stakeholders' collaboration have contributed to making agile a transformation in the software industry in which many companies want to take part. However, driven either by a natural and expected evolution or by contextual factors that challenge the adoption of agile methods as prescribed by their creator(s), software processes in practice mutate into hybrids over time. Are these still agile? In this article, we investigate the question: what makes a software development method agile? We present an empirical study grounded in a large-scale international survey that aims to identify software development methods and practices that improve or tame agility. Based on 556 data points, we analyze the perceived degree of agility in the implementation of standard project disciplines and its relation to used development methods and practices. Our findings suggest that only a small number of participants operate their projects in a purely traditional or agile manner (under 15%). That said, most project disciplines and most practices show a clear trend towards increasing degrees of agility. Compared to the methods used to develop software, the selection of practices has a stronger effect on the degree of agility of a given discipline. Finally, there are no methods or practices that explicitly guarantee or prevent agility. We conclude that agility cannot be defined solely at the process level. Additional factors need to be taken into account when trying to implement or improve agility in a software company. Finally, we discuss the field of software process-related research in the light of our findings and present a roadmap for future research.

cs.SE↗

Catching up with Method and Process Practice: An Industry-Informed Baseline for Researchers

Software development methods are usually not applied by the book. Companies are under pressure to continuously deploy software products that meet market needs and stakeholders' requests. To implement efficient and effective development processes, companies utilize multiple frameworks, methods and practices, and combine these into hybrid methods. A common combination contains a rich management framework to organize and steer projects complemented with a number of smaller practices providing the development teams with tools to complete their tasks. In this paper, based on 732 data points collected through an international survey, we study the software development process use in practice. Our results show that 76.8% of the companies implement hybrid methods. Company size as well as the strategy in devising and evolving hybrid methods affect the suitability of the chosen process to reach company or project goals. Our findings show that companies that combine planned improvement programs with process evolution can increase their process' suitability by up to 5%.

cs.SE↗

Closing the gap between software engineering education and industrial needs

According to different reports, many recent software engineering graduates often face difficulties when beginning their professional careers, due to misalignment of the skills learnt in their university education with what is needed in industry. To address that need, many studies have been conducted to align software engineering education with industry needs. To synthesize that body of knowledge, we present in this paper a systematic literature review (SLR) which summarizes the findings of 33 studies in this area. By doing a meta-analysis of all those studies and using data from 12 countries and over 4,000 data points, this study will enable educators and hiring managers to adapt their education / hiring efforts to best prepare the software engineering workforce.

cs.SE↗