Generative AI is rapidly reshaping Open Source Software (OSS) software development,prompting projects to introduce policies governing AI-assisted contributions. However, little is known about how these policies differ or whether they influence developer experience. We present the first large-scale empirical study of AI governance policies in OSS. Analyzing 29,624 GitHub repositories, we identify 385 projects that adopted AI policies and derive TRACE, a framework capturing five governance dimensions: Transparency, Responsibility, Attribution, Constraints, and Enforcement. We further classify policies into five governance families and estimate their effects using propensity-score matching and longitudinal difference-in-differences analysis. Our results show that AI governance primarily regulates rather than prohibits AI-assisted development. Policy adoption brings maintainer engagement, increased AI disclosure, richer review interactions, and improved code quality while AI-assisted contributions continue to grow. Governance design matters: policies emphasizing transparency and responsibility produced stronger community and quality outcomes than restrictive approaches alone. Our findings show how different AI governance strategies shape developer experience and provide evidence to help OSS communities design effective AI policies.
Yunqi Chen, Thomas Zimmermann, Bianca Trinkenreich· 0 citations
We are witnessing the emergence of Agentic Software Engineering (SE~3.0), where AI agents act as autonomous AI Teammates performing complex tasks such as coding, debugging, and testing. As AI Teammates generate a vast new category of digital artifacts, they introduce unique opportunities and challenges related to human-AI collaboration, trustworthiness, and economic impact. This workshop serves as the premier forum for addressing these challenges, anchored by the launch of the AIDev dataset. Comprising over one million agentic pull requests generated by AI Teammates such as Claude Code, OpenAI Codex, and GitHub Copilot, AIDev provides the empirical evidence needed to understand the behaviors of AI Teammates. This workshop features insights from major industry players and academic pioneers, and aims to define a roadmap for a world where AI Teammates and human developers build the future together.
Hao Li, Haoxiang Zhang, Jie M. Zhang et al.· Proceedings of the 32nd ACM...· 0 citations
Automated program repair (APR) agents are transitioning from research benchmarks to developer workflows, yet they still begin with bug reports written for human developers. While decades of research have established what makes a good bug report for humans (e.g., steps to reproduce, stack traces), it remains unclear whether these features transfer to LLM-based agents. We study this question in two analyses. First, we use statistical modeling to examine associations between 27 bug-report features and repair success across 433 SWE-bench Verified issues attempted by 87 repair agents. We find that fix suggestions, reproduction scripts, repository source code, and localization info are associated with higher resolution likelihood, while longer reports are associated with lower odds. Second, we conduct controlled ablations across 2 models and 17 problem-statement mutations on SWE-bench Pro, varying the information available to an agent while holding the underlying task fixed. We remove or isolate selected bug-report content, delete fault-localization cues, and test structural changes that flatten lists or remove section headers. We find that both models depend on localization cues and expected behavior, and that structural changes alone can reduce solve rates, even without removing any content. The two models diverge in how they handle missing information: Qwen searches more widely and can exhaust its turn budget, while Gemma commits to a plausible interpretation early and patches on it. Our findings indicate that a good bug report for an agent overlaps with, but is not identical to, a good report for a human: agents benefit most from concrete, executable, and well-localized information, whereas some qualities long emphasized for human readers, such as natural language steps to reproduce and readable descriptions, contribute little or even correlate with lower success.
Lara Khatib, N. Mathews, M. Nagappan et al.· 2 citations· ⚡1
This paper presents a developer-centered empirical mixed-methods study to investigate how professional developers engage with Generative AI in their natural work environment, and proposes a rule-of-thumb for selecting an interaction type based on task characteristics.
Charlotte Brandebusemeyer, Kerim Zunic, Thomas Zimmermann et al.· 0 citations
A three-level taxonomy inspired by autonomous driving that distinguishes degrees of autonomy along a roadmap from today’s AI-assisted development workflows to fully autonomous software development in which AI systems autonomously identify demands and design, implement, verify, and maintain software without human oversight is introduced.