Preprint
Aug 2026
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 (SFT) on successful trajectories. However, task success does not guarantee high-quality supervision: successful trajectories...
De-Wu Zheng, Rui Ye, Yanlan Wang et al.
· 3 citations