Prompting LLMs for Code Editing: Struggles and Remedies

Large Language Models (LLMs) are rapidly transforming software engineering, with coding assistants embedded in an IDE becoming increasingly prevalent. While research has focused on improving the tools and understanding developer perceptions, a critical gap exists in understanding how developers actually use these tools in their daily workflows, and, crucially, where they struggle. This paper addresses part of this gap through a multi-phased investigation of developer interactions with an LLM-powered code editing and transformation feature, Transform Code, in an IDE widely used at Google. First, we analyze telemetry logs of the feature usage, revealing that frequent re-prompting can be an indicator of developer struggles with using Transform Code. Second, we conduct a qualitative analysis of unsatisfactory requests, identifying five key categories of information often missing from developer prompts. Finally, based on these findings, we propose and evaluate a tool, AutoPrompter, for automatically improving prompts by inferring missing information from the surrounding code context, leading to a 27% improvement in edit correctness on our test set.

@article{nam2025_2504.20196,
  title={ Prompting LLMs for Code Editing: Struggles and Remedies },
  author={ Daye Nam and Ahmed Omran and Ambar Murillo and Saksham Thakur and Abner Araujo and Marcel Blistein and Alexander Frömmgen and Vincent Hellendoorn and Satish Chandra },
  journal={arXiv preprint arXiv:2504.20196},
  year={ 2025 }
}