.png){kind=icon}
.png){kind=icon}
Return
P-NPR: Practical Neural Program Repair via Learning to Ensemble
.png){kind=icon}
PRE
AI
Z
李
W
B
V
DOI：10.1109/tse.2026.3687916.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
The rapid emergence of Large Language Model (LLM)-based program repair tools has significantly advanced the potential of automated program repair. Nevertheless, traditional Neural Program Repair (NPR) tools continue to offer unique value in resource-constrained or latency-sensitive scenarios due to their lightweight nature. Over 50 such NPR tools have been designed and proven effective at fixing various bugs using only the buggy code as input. Recent studies further demonstrate that combining these tools through ensemble strategies can enhance overall repair performance by leveraging their complementary strengths. However, existing ensemble approaches still suffer from two critical limitations: (1) they rely on manual feature summarization, requiring labor-intensive labeling of bug characteristics, and (2) they ignore the common “all-tools-fail” scenario (e.g., even a set of 15 state-of-the-art tools leaves over 66% of Defects4J bugs unfixed), which incurs unnecessary computational overhead. To address these issues, we propose Practical Neural Program Repair (P-NPR), a novel ensemble strategy that employs multi-label classification to automatically learn to characterize bugs and introduces a dedicated “AllFailure” label to explicitly sidestep futile repair attempts. Experimental results show that P-NPR outperforms the state-of-the-art ensemble strategy (i.e., P-EPR) by over 65% in Top1-accuracy, while reducing runtime by up to 45% and GPU memory usage by up to 23% across evaluated datasets.
Keywords:
Program repair
multi-label classification
Journal
IF:
5.6
Papers:
2.8K
Citations:
1.1W
Organization
Cited Papers