Completion by Comprehension: Guiding Code Generation with Multi-Granularity Understanding

TL;DR

This paper introduces CoCo, a framework that enhances code completion by understanding multi-level structural and semantic context from large codebases, significantly improving accuracy over existing methods.

Contribution

CoCo uniquely integrates static code analysis with graph-based context selection and structure-aware re-ranking to improve code generation quality.

Findings

Achieves up to 20.2% EM improvement on benchmarks.

Effectively captures control flow and semantic dependencies.

Compatible with various code completion models.

Abstract

As code completion task from function-level to repository-level, leveraging contextual information from large-scale codebases becomes a core challenge. However, existing retrieval-augmented generation (RAG) methods typically treat code as plain natural language, relying primarily on shallow semantic matching while overlooking structural semantics and code-specific dependencies. This limits their ability to capture control flow and underlying intent, ultimately constraining the quality of generated code. Therefore, we propose CoCo, a novel framework that enables code Completion by Comprehension of multi-granularity context from large-scale code repositories. CoCo employs static code analysis to extract structured context at the function, file, and project levels, capturing execution logic and semantic dependencies. It then adopts an graph-based multi-granularity context selection mechanism to filter out redundant information and remove noise. Consequently, the information is converted into natural language in a consistent manner, thereby functioning as explicit contextual prompts to guide subsequent code completion. Additionally, a structure-aware code re-ranker mechanism ensures alignment at both semantic and structural levels. Extensive experiments on CrossCodeEval and RepoEval benchmarks demonstrate that CoCo consistently surpasses state-of-the-art baselines, achieving up to 20.2% gains in EM. Moreover, the framework is model-agnostic and can be seamlessly integrated into existing methods, leading to significant performance.