Training on more validated GitHub issue-fix trajectories steadily raises SWE-bench Verified pass@1 from 6.4% to 38.0%, with 47.0% after test-time scaling, and no plateau yet.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs
Training on more validated GitHub issue-fix trajectories steadily raises SWE-bench Verified pass@1 from 6.4% to 38.0%, with 47.0% after test-time scaling, and no plateau yet.