LLM4Code

RepoSim: Evaluating Prompt Strategies for Code Completion via User Behavior Simulation

Large language models (LLMs) have revolutionized code completion tasks. IDE plugins such as Copilot can generate code recommendations, …

Chao Peng, Qinyun Wu, Jiangchao Liu, Jierui Liu, Bo Jiang, Mengqian Xu, Yinghao Wang, Xia Liu, Ping Yang

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

RepoMasterEval: Evaluating Code Completion via Real-World Repositories

With the growing reliance on automated code completion tools in software development, the need for robust evaluation benchmarks has …

Qinyun Wu, Chao Peng, Pengfei Gao, Ruida Hu, Haoyu Gan, Bo Jiang, Jinhe Tang, Zhiwen Deng, Zhanming Guan, Cuiyun Gao, Xia Liu, Ping Yang