Problem
Research questions and friction points this paper is trying to address.
AI coding agents
open-source software
conversational collaboration
vibe-coding
developer interaction
From Conversation to Contribution: Characterizing Coding Agent in Open-Source Software
🤖 AI Summary
This study addresses the limited systematic understanding of how interactions between developers and AI coding assistants influence open-source collaboration, a gap that hinders the effective design and governance of AI-augmented development. By linking 13,360 AI conversation logs to the corresponding development histories of open-source projects and complementing this with developer surveys, the research integrates multi-source data—including GitHub discussions, commits, pull requests, and questionnaire responses—and employs data mining, statistical analysis, and qualitative coding to uncover complex relationships among AI usage patterns, changes in contribution behavior, and developer perceptions. Findings reveal that AI is used more frequently in smaller, less mature projects; while contributor activity increases post-AI adoption, contribution concentration declines without significant deterioration in code quality. Developers generally perceive AI as lowering participation barriers but express concerns about maintainability and knowledge-sharing risks. The work proposes an empirical analytical framework for “vibe-coding” within open-source ecosystems.
📝 Abstract
AI coding assistants such as GitHub Copilot and Cursor have evolved from code-suggestion tools into conversational collaborators, enabling vibe-coding workflows in which developers guide AI-generated code through natural-language dialogue. Although researchers have increasingly recognized the importance of AI coding agents and begun examining their impact on open-source development, a comprehensive understanding of how developers' chat-based interactions with AI relate to subsequent open-source development and collaboration remains limited. This hinders efforts to effectively design, evaluate, and govern AI-assisted open-source software development. To address this gap, we collected 13,360 AI conversation sessions comprising 79,172 user messages from 1,356 OSS repositories, linked them to repository development histories, and complemented this analysis with a targeted developer survey. We find heavier AI use in smaller, less mature, and less collaborative repositories. After AI adoption, projects tended to show more active contributors and lower contributor concentration (p < .001), although communication remained highly concentrated. Code Writing was the dominant chat purpose, and nearly all AI chat sessions were followed by subsequent commits. We find no broad deterioration in code-quality signals or pull request merging rates. However, developers perceive others' AI-generated code as harder to maintain than their own (p = .029) and view AI as lowering barriers to OSS contribution. While most developers (68%) are willing to share their chat, concerns remain around appearing incompetent, increasing reviewer burden, and exposing ideas to competitors. These findings provide a large-scale empirical characterization of AI-assisted OSS contribution and offer practical insights for designing and governing responsible vibe-coding practices in open-source development.
Innovation
Methods, ideas, or system contributions that make the work stand out.
AI coding agents
vibe-coding
open-source software
conversational collaboration
empirical study
🔎 Similar Papers
No similar papers found.
