# RepoGenReflex: Enhancing Repository-Level Code Completion with Verbal Reinforcement and Retrieval-Augmented Generation

arXiv: https://arxiv.org/abs/2409.13122 · HTML: https://mlsanity.com/paper/2409.13122/

## Key facts

- Cited by 6 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 32 references that are in the map.
- First posted on arXiv 19 Sep 2024.

## Placed in

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

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

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis](https://mlsanity.com/paper/2203.13474/) (2022)
- [CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation](https://mlsanity.com/paper/2102.04664/) (2021)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [Generation-Augmented Retrieval for Open-domain Question Answering](https://mlsanity.com/paper/2009.08553/) (2020)
- [Retrieval Augmented Code Generation and Summarization](https://mlsanity.com/paper/2108.11601/) (2021)
- [LongCoder: A Long-Range Pre-trained Language Model for Code Completion](https://mlsanity.com/paper/2306.14893/) (2023)
- [Repository-Level Prompt Generation for Large Language Models of Code](https://mlsanity.com/paper/2206.12839/) (2022)
- [Retrieval-Augmented Generation for Code Summarization via Hybrid GNN](https://mlsanity.com/paper/2006.05405/) (2020)
- [CoTexT: Multi-task Learning with Code-Text Transformer](https://mlsanity.com/paper/2105.08645/) (2021)
- [Pythia: AI-assisted Code Completion System](https://mlsanity.com/paper/1912.00742/) (2019)
- [Repoformer: Selective Retrieval for Repository-Level Code Completion](https://mlsanity.com/paper/2403.10059/) (2024)
- [CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences](https://mlsanity.com/paper/2202.06689/) (2022)
- [RLCoder: Reinforcement Learning for Repository-Level Code Completion](https://mlsanity.com/paper/2407.19487/) (2024)

## Built on by (most cited first, 6 of 6)

- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches](https://mlsanity.com/paper/2510.04905/) (2025)
- [A Survey on Agentic Multimodal Large Language Models](https://mlsanity.com/paper/2510.10991/) (2025)
- [From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence](https://mlsanity.com/paper/2511.18538/) (2025)
- [AlignCoder: Aligning Retrieval with Target Intent for Repository-Level Code Completion](https://mlsanity.com/paper/2601.19697/) (2026)
- [Code Generation by Differential Test Time Scaling](https://mlsanity.com/paper/2605.20473/) (2026)

## Abstract (arXiv)

In real-world software engineering tasks, solving a problem often requires understanding and modifying multiple functions, classes, and files across a large codebase. Therefore, on the repository level, it is crucial to extract the relevant information to achieve accurate code completion effectively. Existing code completion tools have achieved some success, but they struggle to optimize the retrieval and generation process dynamically. In this paper, we propose RepoGenReflex, a generic, dynamic, effective framework to address this challenge. By leveraging the Retrieval-Augmented Generation (RAG) enhanced with Verbal Reinforcement Learning (VRL), it can dynamically choose the optimal results for repository-level code completion. RepoGenReflex uses Reflector to give directional feedback to the next loop. RepoGenReflex chooses the optimal results stored in the Experience cache based on the RAG-VRL loop. To validate the framework's generalization ability, we propose a new benchmark RepoGenEval, which consists of the latest, high-quality real-world repositories in line completion scenarios. Our experiments demonstrate that RepoGenReflex achieves significant improvements after optimizing the Reflector component, resulting in enhanced accuracy and relevance of code completions. Additionally, RepoGenReflex consistently demonstrates superior performance and effectiveness across standard code completion tasks, highlighting the robustness and adaptability of our framework.