# Git-Assistant: Planning-Based Support for Updating Git Repositories

arXiv: https://arxiv.org/abs/2607.09224 · HTML: https://mlsanity.com/paper/2607.09224/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 18 references that are in the map.
- First posted on arXiv 10 Jul 2026.

## Builds on (most cited first, 4 of 4)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Large Language Models: A Survey](https://mlsanity.com/paper/2402.06196/) (2024)
- [How Do Software Developers Use GitHub Actions to Automate Their Workflows?](https://mlsanity.com/paper/2103.12224/) (2021)
- [The GitHub Development Workflow Automation Ecosystems](https://mlsanity.com/paper/2305.04772/) (2023)

## Abstract (arXiv)

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.