5 papers
Effective and Efficient Context Retrieval via Partial Dependency Graph for Repository-Level Code Generation
Zhongxin Liu, Zhonghao Jiang, Zhifan Ye +3
LLM-based repository-level code generation aims to generate code using the context available in a software repository, requiring LLMs to reason over complex code dependencies. Due…
iCoRe: An Iterative Correlation-Aware Retriever for Bug Reproduction Test Generation
Junyi Wang, Jialun Cao, Zhongxin Liu
Automatically generating bug reproduction tests (BRT) from issue descriptions is crucial for software maintenance. LLM-based approaches have shown great potential for this task. Th…
PracRepair: LLM-Empowered Automated Program Repair Inspired by Human-Like Debugging Practices
Yu Cheng, Zhongxin Liu, Zhenchang Xing +3
As software systems grow in scale and complexity, debugging and repair remain costly and time-consuming. Large language models (LLMs) have advanced automated program repair (APR),…
Unit Test Update through LLM-Driven Context Collection and Error-Type-Aware Refinement
Yuanhe Zhang, Zhiquan Yang, Shengyi Pan +1
Unit testing is critical for ensuring software quality and software system stability. The current practice of manually maintaining unit tests suffers from low efficiency and the ri…
Enhancing Project-Specific Code Completion by Inferring Internal API Information
Le Deng, Xiaoxue Ren, Chao Ni +3
Project-specific code completion is a critical task that leverages context from a project to generate accurate code. State-of-the-art methods use retrieval-augmented generation (RA…