Git-Assistant: Planning-Based Support for Updating Git Repositories
2026-07-10 • Software Engineering
Software EngineeringArtificial IntelligenceComputation and Language
AI summaryⓘ
The authors created Git-Assistant, a tool that helps developers use git more easily by understanding natural language commands and turning them into safe and correct git actions. They combined large language models (LLMs) with formal planning to make sure the git commands work well and reduce mistakes. Their tests show that this mix of AI methods makes managing git repositories more reliable than using LLMs alone. This work suggests that combining language understanding with strict reasoning can better assist developers.
version controlgitlarge language modelsLLMsautomated planningnatural language processingrepository managementsoftware developmentAI assistantformal reasoning
Authors
Alfredo Garrachón Ruiz, Tomás de la Rosa, Daniel Borrajo
Abstract
Version control systems are essential for collaborative software development, yet tools like git remain challenging for many practitioners. Recent advances in Large Language Models (LLMs) offer promising capabilities for interpreting developer intent, but their effectiveness in repository management tasks is limited by the need for formal reasoning. This work introduces Git-Assistant, an AI-based assistant that combines LLMs with automated planning to support developers in executing non-trivial git operations. The assistant analyzes repository context, translates natural language requests into actionable command sequences, and incorporates planning techniques to ensure correctness and safety. We present a systematic evaluation methodology using synthetic and randomized git environments, comparing the performance of LLM-only and planning-augmented variants across multiple metrics. Experimental results demonstrate that integrating formal reasoning with LLMs improves reliability and reduces errors in repository management, highlighting the potential of hybrid AI approaches for intelligent developer assistance.