Repairity lifts Qwen2.5-Coder-32B from 38.2% to 62.7% on SWE-bench Verified by distilling Claude's reasoning traces and then fine-tuning with a reward model trained on Claude preferences.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Boosting Open-Source LLMs for Program Repair via Reasoning Transfer and LLM-Guided Reinforcement Learning
Repairity lifts Qwen2.5-Coder-32B from 38.2% to 62.7% on SWE-bench Verified by distilling Claude's reasoning traces and then fine-tuning with a reward model trained on Claude preferences.