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

ACL ARR 2026 January Submission9283 Authors

Keywords: Repository-Level Code Completion, Code LLMs

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.

Paper Type: Long

Research Area: Code Models

Research Area Keywords: code completion,software engineering automation

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models

Languages Studied: english, programming language

Submission Number: 9283