Related papers: When AI Agents Touch CI/CD Configurations: Frequen…
As AI-driven agents become increasingly integrated into the digital ecosystem, they reshape how online advertising is perceived and processed. Particularly in the travel and hotel booking sector, these autonomous systems influence the…
Embodied AI agents increasingly rely on large language models (LLMs) for planning, yet per-step LLM calls impose severe latency and cost. In this paper, we show that embodied tasks exhibit strong plan locality, where the next plan is…
As Software Engineering enters its new era (SE 3.0), AI coding agents increasingly automate software development workflows. However, it remains unclear how exactly these agents recognize and address software energy concerns-an issue growing…
DevOps is a combination of methodologies and tools that improves the software development, build, deployment, and monitoring processes by shortening its lifecycle and improving software quality. Part of this process is CI/CD, which embodies…
The availability of generative Artificial Intelligence (AI) tools such as ChatGPT or GitHub Copilot is reshaping the way in which software is developed, evolved, and maintained. Oftentimes, developers leave traces of such an usage in…
AI coding assistants have transformed software development, raising questions about transparency and attribution practices. We examine the "AI attribution paradox": how developers strategically balance acknowledging AI assistance with…
API misuse introduces security vulnerabilities, system failures, and increases maintenance costs, all of which remain critical challenges in software development. Existing detection approaches rely on static analysis or machine…
Language Model (LM)-based agents remain largely untested in mixed-motive settings where agents must leverage short-term cooperation for long-term competitive goals (e.g., multi-party politics). We introduce Cooperate to Compete (C2C), a…
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…
As AI agents increasingly operate in multi-agent environments, understanding their collective behavior becomes critical for predicting the dynamics of artificial societies. This study examines conformity, the tendency to align with group…
AI-assisted programming tools are widely adopted, yet their practical utility is often undermined by undesired suggestions that interrupt developer workflows and cause frustration. While existing research has explored developer-AI…
AI assistants for coding are on the rise. However one of the reasons developers and companies avoid harnessing their full potential is the questionable security of the generated code. This paper first reviews the current state-of-the-art…
Despite the growing interest in collaborative AI, designing systems that seamlessly integrate human input remains a major challenge. In this study, we developed a task to systematically examine human preferences for collaborative agents. We…
Existing AI agents typically execute multi-step tasks autonomously and only allow user confirmation at the end. During execution, users have little control, making the confirm-at-end approach brittle: a single error can cascade and force a…
Can AI agents predict whether they will succeed at a task? We study agentic uncertainty by eliciting success probability estimates before, during, and after task execution. All results exhibit agentic overconfidence: some agents that…
We analyze 37.5 million deidentified conversations with Microsoft's Copilot between January and September 2025. Unlike prior analyses of AI usage, we focus not just on what people do with AI, but on how and when they do it. We find that how…
The rapid advancements in Generative AI (GenAI) tools, such as ChatGPT and GitHub Copilot, are transforming software engineering by automating code generation tasks. While these tools improve developer productivity, they also present…
LLM-based agentic coding assistants lack persistent memory: they lose coherence across sessions, forget project conventions, and repeat known mistakes. Recent studies characterize how developers configure agents through manifest files, but…
Several advances in deep learning have been successfully applied to the software development process. Of recent interest is the use of neural language models to build tools, such as Copilot, that assist in writing code. In this paper we…
AI-based code assistants are increasingly popular as a means to enhance productivity and improve code quality. This study compares four AI-based code assistants, GitHub Copilot, Tabnine, ChatGPT, and Google Bard, in method generation tasks,…