.png){kind=icon}
.png){kind=icon}
Return
A3-CodGen: A Repository-Level Code Generation Framework for Code Reuse With Local-Aware, Global-Aware, and Third-Party-Library-Aware
.png){kind=icon}
PRE
AI
DOI：10.1109/TSE.2024.3486195.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
LLM-based code generation tools are essential to help developers in the software development process. Existing tools often disconnect with the working context, i.e., the code repository, causing the generated code to be not similar to human developers. In this paper, we propose a novel code generation framework, dubbed A(3)-CodGen, to harness information within the code repository to generate code with fewer potential logical errors, code redundancy, and library-induced compatibility issues. We identify three types of representative information for the code repository: local-aware information from the current code file, global-aware information from other code files, and third-party-library information. Results demonstrate that by adopting the A(3)-CodGen framework, we successfully extract, fuse, and feed code repository information into the LLM, generating more accurate, efficient, and highly reusable code. The effectiveness of our framework is further underscored by generating code with a higher reuse rate, compared to human developers. This research contributes significantly to the field of code generation, providing developers with a more powerful tool to address the evolving demands in software development in practice.
Keywords:
Codes
Libraries
Software development management
Data mining
Benchmark testing
Transformers
Software engineering
Context modeling
Chatbots
Australia
Code generation
repository knowledge mining
code reuse
retrieval-augmented generation
Journal
IF:
5.6
Papers:
2.8K
Citations:
1.1W