ACL Findings2026
CascadeFix: Multi-Location Program Repair via Cascading Planning and Generation
Huan Zhang, Li Kuang, Yang Yang, Yilei Fang, Yingjie Xia
Abstract
Automated Program Repair (APR) is vital for software maintenance. Despite notable advancements, existing methods still face challenges of insufficient bug dependency modeling and inadequate global repair planning when addressing semantically complex multilocation bugs. We propose CASCADEFIX, a multi-location automatic repair method via cascading planning and generation. Firstly, to improve the modeling of semantic and structural dependencies among bugs, three types of bug relationships-Use, Copy, and Nearby-are defined to characterize semantic connection, patch reusability, and contextual interference. Then, to address inadequate global repair planning, a cascading repair planning algorithm is designed to effectively cluster strongly correlated bugs and intelligently assign reasonable repair priorities and operations to each cluster, ensuring the rationality and consistency of global repair. Finally, taking clusters as the basic repair units, a cascading patch generation mechanism is proposed to dynamically integrate intra-cluster dependency information and cross-cluster repair knowledge, producing patches that maintain syntactic correctness and semantic consistency under global dependency constraints. Experiments on Defects4J show that CASCADEFIX resolves 84 multi-location bugs, achieving a 31% improvement over current state-of-the-art methods.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
Lineage
- Automated Program Repair via Conversation: Fixing 162 out of 337 Bugs for $0.42 Each using ChatGPT cites Less training, more repairing please: revisiting automated program repair via zero-shot learning
- Automated Program Repair via Conversation: Fixing 162 out of 337 Bugs for $0.42 Each using ChatGPT cites DLFix: context-based code transformation learning for automated program repair
- Automated Program Repair via Conversation: Fixing 162 out of 337 Bugs for $0.42 Each using ChatGPT cites Automated Program Repair in the Era of Large Pre-trained Language Models
- Less training, more repairing please: revisiting automated program repair via zero-shot learning cites DLFix: context-based code transformation learning for automated program repair
- Automated Program Repair in the Era of Large Pre-trained Language Models cites Less training, more repairing please: revisiting automated program repair via zero-shot learning
- Automated Program Repair in the Era of Large Pre-trained Language Models cites DLFix: context-based code transformation learning for automated program repair
- DEAR: A Novel Deep Learning-based Approach for Automated Program Repair cites DLFix: context-based code transformation learning for automated program repair
Builds on13
- Automated Program Repair in the Era of Large Pre-trained Language ModelsChunqiu Steven Xia, Yuxiang Wei, Lingming ZhangICSE 2023 · 321 citations
- Less training, more repairing please: revisiting automated program repair via zero-shot learningChunqiu Steven Xia, Lingming ZhangFSE 2022 · 223 citations
- DLFix: context-based code transformation learning for automated program repairYi Li, Shaohua Wang, Tien N. NguyenICSE 2020 · 201 citations
- Automated Program Repair via Conversation: Fixing 162 out of 337 Bugs for $0.42 Each using ChatGPTChunqiu Steven Xia, Lingming ZhangISSTA 2024 · 105 citations
- DEAR: A Novel Deep Learning-based Approach for Automated Program RepairYi Li, Shaohua Wang, Tien N. NguyenICSE 2022 · 91 citations
Related papers
- ITER: Iterative Neural Repair for Multi-Location PatchesHe Ye, Martin MonperrusICSE 2024 · 39 citations
- Enhancing LLM-Based Bug Reproduction via Code Entity Retrieval and Test Case RepairHao Ding, Yanjie Jiang, Yuxia Zhang, Hui LiuISSTA 2026
- Detecting, Creating, Repairing, and Understanding Indivisible Multi-Hunk BugsQi Xin, Haojun Wu, Jinran Tang, Xinyu Liu et al.FSE 2024 · 3 citations
- One Size Does Not Fit All: Multi-granularity Patch Generation for Better Automated Program RepairBo Lin, Shangwen Wang, Ming Wen, Liqian Chen et al.ISSTA 2024 · 10 citations
- Extracting Concise Bug-Fixing Patches from Human-Written Patches in Version Control SystemsYanjie Jiang, Hui Liu, Nan Niu, Lu Zhang et al.ICSE 2021 · 38 citations
