An Empirical Study of Proactive Coding Assistants in Real-World Software Development

ArXi:2605.05700v1 Announce Type: cross Large language model (LLM)-based coding assistants have made substantial progress, yet most systems remain reactive, requiring developers to explicitly formulate their needs. Proactive coding assistants aim to infer latent developer intent from integrated development environment (IDE) interactions and repository context, thereby reducing interaction overhead and ing seamless assistance. However, research in this direction is limited by the scarcity of large-scale real-world developer behavior data.