CodeLift: Your Test Suite Is Secretly a Dense SWE Curriculum
The pass-all-test binary reward has become a standard recipe for training software engineering agents, but its sparsity eliminates difference of partially correct patches. The test pass-rate is a natural alternative. However, we find that it is not a reliable indicator of patch quality. A functionality being tested can...
Junjielong Xu, Hua-Chao Zhu, Alyssa Wu et al.
· 0 citations