CodingGenie: A Proactive LLM-Powered Programming Assistant

2025-03-18

AI Summary

Existing LLM-based programming tools require explicit user invocation, hindering seamless integration into development workflows. This paper introduces CodingGenie—the first proactive, editor-embedded programming assistant that operates without manual triggering, automatically generating context-aware suggestions (e.g., bug fixes, unit test generation) based on real-time code state, while supporting customizable task descriptions and suggestion-type filtering. Its key contributions are: (1) the first fully proactive LLM-assisted programming paradigm; (2) a lightweight plugin architecture coupled with dynamic prompt engineering to ensure low-latency response; and (3) context-aware reasoning and fine-grained suggestion filtering to enhance relevance and precision. Empirical evaluation demonstrates that CodingGenie significantly reduces context-switching frequency and improves task completion efficiency. The open-source implementation is publicly available to support reproducible research and community-driven extension.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Machine Learning: Large Multimodal Models (LMMs)
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

While developers increasingly adopt tools powered by large language models (LLMs) in day-to-day workflows, these tools still require explicit user invocation. To seamlessly integrate LLM capabilities to a developer's workflow, we introduce CodingGenie, a proactive assistant integrated into the code editor. CodingGenie autonomously provides suggestions, ranging from bug fixing to unit testing, based on the current code context and allows users to customize suggestions by providing a task description and selecting what suggestions are shown. We demonstrate multiple use cases to show how proactive suggestions from CodingGenie can improve developer experience, and also analyze the cost of adding proactivity. We believe this open-source tool will enable further research into proactive assistants. CodingGenie is open-sourced at https://github.com/sebzhao/CodingGenie/ and video demos are available at https://sebzhao.github.io/CodingGenie/.

Problem

• Developers need explicit invocation for LLM tools.
• CodingGenie integrates LLM capabilities into code editors.
• CodingGenie autonomously suggests bug fixes and unit tests.

Innovation

• Proactive LLM-powered programming assistant integrated into code editor.
• Autonomously provides context-based suggestions for bug fixing and testing.
• Allows user customization of suggestions via task descriptions and selection.