RepoHyper: Search-Expand-Refine on Semantic Graphs for Repository-Level Code Completion
Huy N. Phan, Hoang N. Phan, Tien N. Nguyen, Nghi D. Q. Bui · 2025
Code Large Language Models (CodeLLMs) have demonstrated impressive proficiency in code completion tasks. However, they often fall short of fully understanding the extensive context of a project repository, such as the intricacies of relevant files and class hierarchies, which can result in less precise completions. To overcome these limitations, we present RepoHyper, a multifaceted framework designed to address the complex challenges associated with the completion of code at the repository level. Central to RepoHyper is the Repo-Level Semantic Graph (RSG), a novel semantic graph structure that encapsulates the vast context of code repositories. Furthermore, RepoHyper leverages Expand and Refine retrieval method, including a graph expansion and a link prediction algorithm applied to the RSG, enabling effective retrieval and prioritization of relevant code snippets. Our evaluations show that RepoHyper markedly outperforms existing techniques in repository-level code completion, showcasing enhanced accuracy across various datasets when compared to several strong baselines.