跳到主要导航 跳到搜索 跳到主要内容

Fine-Grained Repair Knowledge Organization for Knowledge-Guided Automated Program Repair

  • China Research Institute of Radiowave Propagation
  • Xi'an Jiaotong University
  • State-Owned Factory No. 5137

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

Template-based automated program repair (APR) exposes explicit repair knowledge, but existing template inventories are often too coarse to act as reusable knowledge units. We therefore study fine-grained repair knowledge organization, which starts from coarse template families, builds multi-view representations of historical bug-fix pairs, discovers finer repair groups, and abstracts them into structured knowledge entries. The resulting knowledge base supports retrieval, classifier-based selection, and retrieval-to-classifier reranking, and is grounded in localization-enhanced prompts for patch generation. On an internal Recoder workflow, the approach constructs a non-trivial inventory of 184 accepted fine-grained templates and improves repair over bug-only conditioning. On Defects4J, retrieval is stronger in the top-1 regime, while larger candidate budgets favor classifier or rerank selection. On the full Defects4J 1.2 benchmark, knowledge-guided repair substantially outperforms the template-free bug-only baseline, and the same trend remains visible across both Qwen and Llama.

源语言英语
主期刊名Advanced Intelligent Computing Technology and Applications - 22nd International Conference on Intelligent Computing, ICIC 2026, Proceedings
编辑De-Shuang Huang, Yijie Pan, Chuanlei Zhang, Wei Chen, Prashan Premaratne
出版商Springer Science and Business Media Deutschland GmbH
610-622
页数13
ISBN(印刷版)9789819234493
DOI
出版状态已出版 - 2027
活动22nd International Conference on Intelligent Computing, ICIC 2026 - Toronto, 加拿大
期限: 22 7月 202626 7月 2026

丛书

姓名Lecture Notes in Computer Science
16667 LNCS
ISSN(印刷版)0302-9743
ISSN(电子版)1611-3349

会议

会议22nd International Conference on Intelligent Computing, ICIC 2026
国家/地区加拿大
Toronto
时期22/07/2626/07/26

学术指纹

探究 'Fine-Grained Repair Knowledge Organization for Knowledge-Guided Automated Program Repair' 的科研主题。它们共同构成独一无二的学术指纹。

引用此