# CodeRAG: Finding Relevant and Necessary Knowledge for Retrieval-Augmented Repository-Level Code Completion

arXiv: https://arxiv.org/abs/2509.16112 · HTML: https://mlsanity.com/paper/2509.16112/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in RAG for code, one of 15 directions in Retrieval-augmented generation.
- Builds on 15 of its 29 references that are in the map.
- First posted on arXiv 19 Sep 2025.

## Placed in

- Retrieval-augmented generation / [RAG for code](https://mlsanity.com/rag/rag-for-code/)

## Builds on (most cited first, 15 of 15)

- [RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval](https://mlsanity.com/paper/2401.18059/) (2024)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [UniXcoder: Unified Cross-Modal Pre-training for Code Representation](https://mlsanity.com/paper/2203.03850/) (2022)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting](https://mlsanity.com/paper/2306.17563/) (2023)
- [CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion](https://mlsanity.com/paper/2310.11248/) (2023)
- [CoCoMIC: Code Completion By Jointly Modeling In-file and Cross-file Context](https://mlsanity.com/paper/2212.10007/) (2022)
- [Pythia: AI-assisted Code Completion System](https://mlsanity.com/paper/1912.00742/) (2019)
- [Code Completion with Neural Attention and Pointer Networks](https://mlsanity.com/paper/1711.09573/) (2017)
- [Dataflow-Guided Retrieval Augmentation for Repository-Level Code Completion](https://mlsanity.com/paper/2405.19782/) (2024)
- [GraphCoder: Enhancing Repository-Level Code Completion via Code Context Graph-based Retrieval and Language Model](https://mlsanity.com/paper/2406.07003/) (2024)
- [REPOFUSE: Repository-Level Code Completion with Fused Dual Context](https://mlsanity.com/paper/2402.14323/) (2024)
- [Code Completion by Modeling Flattened Abstract Syntax Trees as Graphs](https://mlsanity.com/paper/2103.09499/) (2021)
- [BIDER: Bridging Knowledge Inconsistency for Efficient Retrieval-Augmented LLMs via Key Supporting Evidence](https://mlsanity.com/paper/2402.12174/) (2024)
- [A Survey of Source Code Search: A 3-Dimensional Perspective](https://mlsanity.com/paper/2311.07107/) (2023)

## Built on by (most cited first, 12 of 12)

- [Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches](https://mlsanity.com/paper/2510.04905/) (2025)
- [Beyond the Prompt: An Empirical Study of Cursor Rules](https://mlsanity.com/paper/2512.18925/) (2025)
- [Specification-Based Code-Text-Code Reengineering for LLM-Mediated Software Evolution](https://mlsanity.com/paper/2605.25232/) (2026)
- [RepoShapley: Shapley-Enhanced Context Filtering for Repository-Level Code Completion](https://mlsanity.com/paper/2601.03378/) (2026)
- [A Study on the Impact of Fault localization Granularity for Repository-Scale Code Repair Tasks](https://mlsanity.com/paper/2604.00167/) (2026)
- [An Empirical Study of Proactive Coding Assistants in Real-World Software Development](https://mlsanity.com/paper/2605.05700/) (2026)
- [When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context](https://mlsanity.com/paper/2605.14478/) (2026)
- [Library-Aware Doubles and Iterative Repair for Large Language Model-Generated Unit Tests in OpenSIL Firmware](https://mlsanity.com/paper/2606.19725/) (2026)
- [Repository-Level Solidity Code Generation with Large Language Models: From Prompting to Fine-Tuning](https://mlsanity.com/paper/2606.19988/) (2026)
- [SemChunk-C: Semantic Segmentation for C Code](https://mlsanity.com/paper/2606.23697/) (2026)
- [ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation](https://mlsanity.com/paper/2607.08691/) (2026)
- [SynH-Rank: Quality-Aware Code Search via Diverse Data Synthesis and Hierarchical Ranking Training](https://mlsanity.com/paper/2607.17139/) (2026)

## Abstract (arXiv)

Repository-level code completion automatically predicts the unfinished code based on the broader information from the repository. Recent strides in Code Large Language Models (code LLMs) have spurred the development of repository-level code completion methods, yielding promising results. Nevertheless, they suffer from issues such as inappropriate query construction, single-path code retrieval, and misalignment between code retriever and code LLM. To address these problems, we introduce CodeRAG, a framework tailored to identify relevant and necessary knowledge for retrieval-augmented repository-level code completion. Its core components include log probability guided query construction, multi-path code retrieval, and preference-aligned BestFit reranking. Extensive experiments on benchmarks ReccEval and CCEval demonstrate that CodeRAG significantly and consistently outperforms state-of-the-art methods. The implementation of CodeRAG is available at https://github.com/KDEGroup/CodeRAG.