cs.CLNov 5, 2026

Enhancing Repository-Level Code Completion with Reinforcement Learning in Real-World Scenarios

Authors: Zhenlong Dai, Zhuoluo Zhao, Xiu Tang, Sai Wu, Chang Yao, Zhipeng Gao, Jingyuan Chen

Organizations: Zhejiang University · Innovation and Management Center, School of Software Technology (Ningbo), Zhejiang University

Abstract

The rapid development of large language models (LLMs) for code, which closely aligns with the practical needs of real-world software development, has sparked growing attention in repository-level code completion. However, existing Code LLMs present challenges in focusing on suitable contexts from the repository and in deeply reasoning about cross-file dependencies. To address these challenges, we propose a novel reinforcement learning framework for repository-level code completion. To better understand both in-file and cross-file contexts, we employ identifier-driven intent recognition to capture completion intent, thereby improving the model's performance in real-world scenarios. To enhance cross-file reasoning, we propose a reward-driven completion learning to effectively reward in complex repository completion scenarios. To guide LLMs in completing code that aligns with intended functionality and repository context, we introduce a selective-exploration strategy that directs the model to focus on low-confidence, high-reward tokens, promoting the exploration of valuable, underexplored completion patterns. Experimental results show that our approach significantly improves the performance of Code LLMs. The code and the dataset are available at https://github.com/zhenlongDai/RepoCompletion.

Figures & tables

Appendix figures & tables4 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. ReCUBE: Evaluating Repository-Level Context Utilization in Code Generation

    Mar 26, 2026Jiseung Hong, Benjamin G. Ascoli, Jinho D. ChoiRepository-Level Code GenerationCode Generation Evaluation