# Automated Customization of LLMs for Enterprise Code Repositories Using Semantic Scopes

arXiv: https://arxiv.org/abs/2602.05780 · HTML: https://mlsanity.com/paper/2602.05780/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 16 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Builds on (most cited first, 11 of 11)

- [A Survey on Large Language Models for Code Generation](https://mlsanity.com/paper/2406.00515/) (2024)
- [MapCoder: Multi-Agent Code Generation for Competitive Problem Solving](https://mlsanity.com/paper/2405.11403/) (2024)
- [CodeRAG-Bench: Can Retrieval Augment Code Generation?](https://mlsanity.com/paper/2406.14497/) (2024)
- [A Theory on Adam Instability in Large-Scale Machine Learning](https://mlsanity.com/paper/2304.09871/) (2023)
- [Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completion](https://mlsanity.com/paper/2405.19782/) (2024)
- [EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations](https://mlsanity.com/paper/2410.22821/) (2024)
- [HumanEvo: An Evolution-aware Benchmark for More Realistic Evaluation of Repository-level Code Generation](https://mlsanity.com/paper/2406.06918/) (2024)
- [CoCoST: Automatic Complex Code Generation with Online Searching and Correctness Testing](https://mlsanity.com/paper/2403.13583/) (2024)
- [Smaller but Better: Self-Paced Knowledge Distillation for Lightweight yet Effective LCMs](https://mlsanity.com/paper/2408.03680/) (2024)
- [Improving FIM Code Completions via Context & Curriculum Based Learning](https://mlsanity.com/paper/2412.16589/) (2024)
- [RAG or Fine-tuning? A Comparative Study on LCMs-based Code Completion in Industry](https://mlsanity.com/paper/2505.15179/) (2025)

## Abstract (arXiv)

Code completion (CC) is a task frequently used by developers when working in collaboration with LLM-based programming assistants. Despite the increased performance of LLMs on public benchmarks, out of the box LLMs still have a hard time generating code that aligns with a private code repository not previously seen by the model's training data. Customizing code LLMs to a private repository provides a way to improve the model performance. In this paper we present our approach for automated LLM customization based on semantic scopes in the code. We evaluate LLMs on real industry cases with two private enterprise code repositories with two customization strategies: Retrieval-Augmented Generation (RAG) and supervised Fine-Tuning (FT). Our mechanism for ingesting the repository's data and formulating the training data pairs with semantic scopes helps models to learn the underlying patterns specific to the repository, providing more precise code to developers and helping to boost their productivity. The code completions of moderately sized customized models can be significantly better than those of uncustomized models of much larger capacity. We also include an analysis of customization on two public benchmarks and present opportunities for future work.