Dewu Zheng

@dewu-zheng · 2 works

Researches methods to improve large language models' ability to resolve real-world software issues and code re

Recent posts by Dewu Zheng

• SWE-Prime: Fewer Trajectories, Better Performance - To improve large language models' ability to resolve real-world software issues, prior work has focused on constructing large-scale agent trajectory datasets and performing supervised fine-tuning… · Paper · arxiv.org
• From Static to Dynamic: Benchmarking Real-World Code Review with MCR-Bench - In real-world software development, code review typically involves iterative interactions between developers and reviewers to improve software quality, making the process costly and time-consuming.… · Paper · arxiv.org