软件工程
Repository-level fault localization (FL) and automated program repair (APR) require an agent to identify the relevant code units across files, follow call and data dependencies, and generate a valid patch. Existing graph-based systems…
This report describes ARIS (Auto-Research-in-sleep), an open-source research harness for autonomous research, including its architecture, assurance mechanisms, and early deployment experience. The performance of agent systems built on LLMs…
Large Language Models (LLMs) are increasingly deployed to generate code for human-centered applications where demographic fairness is critical. However, existing evaluations focus almost exclusively on functional correctness, leaving social…
Multimodal large language models (MLLMs) are increasingly used to translate visual artifacts into code, from UI mockups into HTML to scientific plots into Python scripts. A circuit diagram can be viewed as a visual domain-specific language…
Continuous Integration (CI) enforces repository-level correctness through multi-stage workflows and is central to modern software development, yet diagnosing and repairing CI failures remains challenging. Unlike traditional program repair,…
This paper explores the effectiveness of modular randomized testing for object oriented programs in Java. Modular testing involves testing individual components of a program in isolation. Often times, for effective test generation, a series…
Programmers are turning to AI coding assistants to answer questions about their code. Benchmarks are needed to soundly evaluate these systems and understand their performance. To enable such a study, we curate a benchmark of real-world…
Syntax highlighting is a critical feature in modern software development environments, enhancing code readability and developer productivity. However, delivering accurate highlighting in real time remains challenging for online and…
Issue-to-commit link recovery in software repositories is fundamental to software traceability and project management, yet it remains a challenging task. Prior studies show that only about 42.2% of issues on GitHub are correctly linked to…
In practice, rigorous reasoning is often a key driver of correct code, while Reinforcement Learning (RL) for code generation often neglects optimizing reasoning quality. Bringing process-level supervision into RL is appealing, but it faces…
Greybox fuzzing is one of the most popular methods for detecting software vulnerabilities, which conducts a biased random search within the program input space. To enhance its effectiveness in achieving deep coverage of program behaviors,…
The promise of Large Language Models in automated software engineering is often measured by functional correctness, overlooking the critical issue of long term maintainability. This paper presents a systematic audit of technical debt in…
State-of-the-art Large Language Models (LLMs) excel in code generation at the function level. However, the output quality significantly declines when scaling to repository-level systems. Current workflows relying only on natural language…
Software engineering increasingly involves making high-stakes decisions under uncertainty, using signals from code, field data, and socio-technical processes. Recent AI-driven support (e.g., anomaly detection, predictive analytics, AIOps,…
Competitive program generation aims to automatically produce correct and efficient solutions for programming-contest problems under strict time and memory constraints. Existing LLM-based approaches often fail to perform explicit algorithmic…
Large language models struggle with understanding codebases beyond a certain scale -- repositories with hundreds of thousands of lines of code. Existing methods -- retrieval, summarization, agent exploration -- each construct a different…
In this paper, we conducted an SLR on the state of user modeling in the MDE domain. Results show a diverse set of disconnected proposals, covering a partial number of dimensions with an emphasis on those characteristics that are easier to…
We analyze code review interactions for AI-generated pull requests (PRs) on GitHub using the AIDev dataset and compare them to human-authored PRs within the same repositories. We find that most AI-generated PRs receive no review and, when…
High-quality commit messages are critical for maintaining software projects, yet ensuring their consistency and informativeness remains a practical challenge. While the Conventional Commits Specification (CCS) provides a structured format…
Frontier software engineering agents have saturated short-horizon benchmarks while regressing on the work that constitutes senior engineering: long-horizon, multi-engineer, ambiguous-specification deliverables. This paper takes a position…