Large Language Models

A Real-World Benchmark for Evaluating Fine-Grained Issue Solving Capabilities of Large Language Models
Automatically resolving software issues is crucial for software development in practice, impacting the software quality and user …
Ruida Hu, Chao Peng, Jingyi Ren, Bo Jiang, Xiangxin Meng, Qinyun Wu, Pengfei Gao, Xinchen Wang, Cuiyun Gao
PDF Cite DOI
AEGIS: An Agent-based Framework for General Bug Reproduction from Issue Descriptions
In software maintenance, bug reproduction is essential for effective fault localization and repair. Manually writing reproduction …
Xinchen Wang, Pengfei Gao, Xiangxin Meng, Chao Peng, Ruida Hu, Yun Lin, Cuiyun Gao
PDF Cite DOI
ContextModule: Improving Code Completion via Repository-level Contextual Information
Large Language Models (LLMs) have demonstrated impressive capabilities in code completion tasks, where they assist developers by …
Zhanming Guan, Junlin Liu, Jierui Liu, Chao Peng, Dexin Liu, Ningyuan Sun, Bo Jiang, Wenchao Li, Jie Liu, Hang Zhu
PDF Cite DOI
An Empirical Study on LLM-based Agents for Automated Bug Fixing
Large language models (LLMs) and LLM-based Agents have been applied to fix bugs automatically, demonstrating the capability in …
Xiangxin Meng, Zexiong Ma, Pengfei Gao, Chao Peng
PDF Cite DOI
MarsCode Agent: AI-native Automated Bug Fixing
Recent advances in large language models (LLMs) have shown significant potential to automate various software development tasks, …
Yizhou Liu, Pengfei Gao, Xinchen Wang, Jie Liu, Yexuan Shi, Zhao Zhang, Chao Peng
PDF Cite DOI