AIRCoder: Adaptive Integration of Multi-dimensional Retrieval for Repository-level Code Completion
Year: 2026
Type: conference-paper
Abstract: Repository-level code completion relies on retrieval strategies to select relevant context from large codebases.Most existing methods employ single-dimensional retrieval based on textual similarity or dependency existence, leading to inconsistent performance across completion scenarios.Even task-adaptive and hybrid methods incur high computational costs while failing to explicitly consider structural hierarchy for retrieving functionally similar code.We introduce AIRCoder, a multidimensional retrieval framework that combines eight complementary metrics across three dimensions: textual similarity, dependency existence, and structural hierarchy.By proposing a structure-preserving chunking strategy and lightweight fusion module, AIRCoder learns context-dependent weights to adaptively integrate retrieval metrics for each query.Experiments on CrossCodeEval and RepoEval demonstrate that AIRCoder achieves an average improvement of 4.63% in exact match over the best baseline, with 10.2× higher efficiency and strong cross-language generalization across Python, Java, C#, and TypeScript. 1
Authors: Chuanqi Shi, Miao Gao, Zhiqiang Gao
Institutions: Southeast University, Southeast University
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W7166833541