Enhancing Repository-Level Code Generation with Integrated Contextual Information

2024-06-05 · Zhiyuan Pan, Xing Hu, Xin Xia, Xiaohu Yang

Large language models (LLMs) have demonstrated remarkable capabilities in code generation tasks. However, repository-level code generation presents unique challenges, particularly due to the need to utilize information spread across multiple files within a repository. Existing retrieval-based approaches sometimes fall short as they are limited in obtaining a broader and deeper repository context. In this paper, we present CatCoder, a novel code generation framework designed for statically typed programming languages. CatCoder enhances repository-level code generation by integrating relevant code and type context. Specifically, it leverages static analyzers to extract type dependencies and merges this information with retrieved code to create comprehensive prompts for LLMs. To evaluate the effectiveness of CatCoder, we adapt and construct benchmarks that include 199 Java tasks and 90 Rust tasks. The results show that CatCoder outperforms the RepoCoder baseline by up to 17.35%, in terms of pass@k score. Furthermore, the generalizability of CatCoder is assessed using various LLMs, including both code-specialized models and general-purpose models. Our findings indicate consistent performance improvements across all models, which underlines the practicality of CatCoder.

📄 PDF Abstract BibTeX arXiv:2406.03283

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation

2026-07-09 · QiHong Chen, Aaron Imani, Iftekhar Ahmed arxiv

Repository-level code generation requires implementing target functions while accounting for complex cross-file dependencies and project-specific conventions. Existing retrieval methods predominantly rely on lexical, str…

Enhancing LLM-Based Coding Tools through Native Integration of IDE-Derived Static Context

2024-02-06 · Yichen Li, Yun Peng, Yintong Huo, Michael R. Lyu

Large Language Models (LLMs) have achieved remarkable success in code completion, as evidenced by their essential roles in developing code assistant services such as Copilot. Being trained on in-file contexts, current LL…

Code Completion

A Review of Repository Level Prompting for LLMs

2023-12-15 · Douglas Schonholtz

As coding challenges become more complex, recent advancements in Large Language Models (LLMs) have led to notable successes, such as achieving a 94.6\% solve rate on the HumanEval benchmark. Concurrently, there is an inc…

Code Completion Code Generation HumanEval Retrieval

ReCUBE: Evaluating Repository-Level Context Utilization in Code Generation

2026-03-26 · Jiseung Hong, Benjamin G. Ascoli, Jinho D. Choi arxiv

Large Language Models (LLMs) have recently emerged as capable coding assistants that operate over large codebases through either agentic exploration or full-context generation. Existing benchmarks capture a broad range o…

Code Generation

RAMBO: Enhancing RAG-based Repository-Level Method Body Completion

2024-09-23 · Tuan-Dung Bui, Duc-Thieu Luu-Van, Thanh-Phat Nguyen, Thu-Trang Nguyen 외

Code completion is essential in software development, helping developers by predicting code snippets based on context. Among completion tasks, Method Body Completion (MBC) is particularly challenging as it involves gener…

Code Completion Code Generation RAG