Related papers: Code Change Characteristics and Description Alignm…
LLM-based autonomous coding agents have reshaped software development. While these agents excel at code generation, open questions persist about the long-term maintainability of AI-generated code. This study empirically investigates the…
Software Engineering 3.0 marks a paradigm shift in software development, in which AI coding agents are no longer just assistive tools but active contributors. While prior empirical studies have examined productivity gains and acceptance…
The rapid adoption of AI coding agents is fundamentally shifting software developers' roles from code authors to code reviewers. While developers spend a significant portion of their time reading and comprehending code, the linguistic…
The integration of AI agents as coding assistants into software development has raised questions about the long-term viability of AI agent-generated code. A prevailing hypothesis within the software engineering community suggests this code…
Developers now have access to a growing array of increasingly autonomous AI tools for software development. While many studies examine copilots that provide chat assistance or code completions, evaluations of coding agents -- which can…
Automated Program Repair (APR) agents leverage Large Language Models (LLMs) to autonomously diagnose and fix software bugs through reasoning, planning, and tool use. Despite impressive leaderboard gains on benchmarks such as SWE-bench,…
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…
We investigate whether giving LLM agents the collaborative tools and autonomy that humans naturally use for problem solving can improve their performance. We equip Claude Code agents with MCP-based social media and journaling tools and…
Human languages provide efficient systems for expressing numerosities, but whether the sheer pressure to communicate is enough for numerical representations to arise in artificial agents, and whether the emergent codes resemble human…
As AI code assistants become increasingly integrated into software development workflows, understanding how their code compares to human-written programs is critical for ensuring reliability, maintainability, and security. In this paper, we…
Here we examine how AI agent "personalities" interact with human personalities to shape human-AI collaboration and performance. In a large-scale, preregistered randomized experiment, we paired 1,258 participants with AI agents prompted to…
Large Language Models based on transformer algorithms have revolutionized Artificial Intelligence by enabling verbal interaction with machines akin to human conversation. These AI agents have surpassed the Turing Test, achieving confusion…
LLM-based software engineering is influencing modern software development. In addition to correctness, prior studies have also examined the performance of software artifacts generated by AI agents. However, it is unclear how exactly the…
We introduce SWE-PRBench, a benchmark of 350 pull requests with human-annotated ground truth for evaluating AI code review quality. Evaluated against an LLM-as-judge framework validated at kappa=0.75, 8 frontier models detect only 15-31% of…
As a maintainer of an open source software project, you are usually happy about contributions in the form of pull requests that bring the project a step forward. Past studies have shown that when reviewing a pull request, not only its…
The rise of AI agents is transforming how software can be built. The promise of agents is that developers might write code quicker, delegate multiple tasks to different agents, and even write a full piece of software purely out of natural…
Modern AI agents optimize programs by refactoring source code to trigger trusted compiler transformations. This preserves program semantics and reduces source code pollution, making the program easier to maintain and portable across…
To understand the impacts of AI-driven coding tools on engineers' workflow and work environment, we utilize the Jellyfish platform to analyze indicators of change. Key indicators are derived from Allocations, Coding Fraction vs. PR…
Behavioral analysis of tutoring dialogues is essential for understanding student learning, yet manual coding remains a bottleneck. We present a methodology where LLM coding agents autonomously improve the prompts used by LLM classifiers to…
Pull-based development has enabled numerous volunteers to contribute to open-source projects with fewer barriers. Nevertheless, a considerable amount of pull requests (PRs) with valid contributions are abandoned by their contributors,…