Hierarchical Knowledge Injection for Improving LLM-based Program Repair
This program is tentative and subject to change.
Prompting LLMs with bug-related context (e.g., error messages, stack traces) improves automated program repair, but many bugs still remain unresolved. In real-world projects, developers often rely on broader repository and project-level context beyond the local code to resolve such bugs. In this paper, we investigate how automatically extracting and providing such knowledge can improve LLM-based program repair. We propose a layered knowledge injection framework that incrementally augments LLMs with structured context. It starts with the Bug Knowledge Layer, which includes information such as the buggy function and failing tests; expands to the Repository Knowledge Layer, which adds structural dependencies, related files, and commit history; and finally injects the Project Knowledge Layer, which incorporates relevant details from documentation and previously fixed bugs. We evaluate this framework on a dataset of 314 bugs from BugsInPy using two LLMs (Llama 3.3 and GPT-4o-mini), and analyze fix rates across six bug types. By progressively injecting knowledge across layers, our approach achieves a fix rate of 79% (250/314) using Llama 3.3, a significant improvement of 23% over previous work. All bug types show improvement with the addition of repository-level context, while only a subset benefit further from project-level knowledge, highlighting that different bug types require different levels of contextual information for effective repair. We also analyze the remaining unresolved bugs and find that more complex and structurally isolated bugs, such as Program Anomaly and GUI bugs, remain difficult even after injecting all available information. Our results show that layered context injection improves program repair and suggest the need for interactive and adaptive APR systems.
This program is tentative and subject to change.
Mon 17 NovDisplayed time zone: Seoul change
11:00 - 12:30 | |||
11:00 10mTalk | Defects4C: Benchmarking Large Language Model Repair Capability with C/C++ Bugs Research Papers Jian Wang Nanyang Technological University, Xiaofei Xie Singapore Management University, Qiang Hu Tianjin University, Shangqing Liu Nanjing University, Jiongchi Yu Singapore Management University, Jiaolong Kong Singapore Management University, Yi Li Nanyang Technological University | ||
11:10 10mTalk | MORepair: Teaching LLMs to Repair Code via Multi-Objective Fine-Tuning Journal-First Track Boyang Yang Yanshan University; Beijing JudaoYouda Network Technology, Haoye Tian Aalto University, Jiadong Ren Yanshan University, Hongyu Zhang Chongqing University, Jacques Klein University of Luxembourg, Tegawendé F. Bissyandé University of Luxembourg, Claire Le Goues Carnegie Mellon University, Shunfu Jin Yanshan University Link to publication DOI Pre-print | ||
11:20 10mTalk | When Fine-Tuning LLMs Meets Data Privacy: An Empirical Study of Federated Learning in LLM-Based Program Repair Journal-First Track Wenqiang LUO City University of Hong Kong, Jacky Keung City University of Hong Kong, Boyang Yang Yanshan University; Beijing JudaoYouda Network Technology, He Ye University College London (UCL), Claire Le Goues Carnegie Mellon University, Tegawendé F. Bissyandé University of Luxembourg, Haoye Tian Aalto University, Xuan-Bach D. Le University of Melbourne | ||
11:30 10mTalk | Test-based Patch Clustering for Automatically-Generated Patches Assessment Journal-First Track Matias Martinez Universitat Politècnica de Catalunya (UPC), Maria Kechagia National and Kapodistrian University of Athens, Anjana Perera Oracle Labs, Australia, Justyna Petke University College London, Federica Sarro University College London, Aldeida Aleti Monash University | ||
11:40 10mTalk | Hierarchical Knowledge Injection for Improving LLM-based Program Repair Research Papers Ramtin Ehsani Drexel University, Esteban Parra Rodriguez Belmont University, Sonia Haiduc Florida State University, Preetha Chatterjee Drexel University, USA | ||
11:50 10mTalk | Characterizing Multi-Hunk Patches: Divergence, Proximity, and LLM Repair Challenges Research Papers Noor Nashid University of British Columbia, Daniel Ding University of British Columbia, Keheliya Gallaba Centre for Software Excellence, Ahmed E. Hassan Queen’s University, Ali Mesbah University of British Columbia | ||
12:00 10mTalk | Reinforcement Learning for Mutation Operator Selection in Automated Program Repair Journal-First Track Carol Hanna University College London, Aymeric Blot University of Rennes, IRISA / INRIA, Justyna Petke University College London | ||
12:10 10mTalk | APRMCTS: Improving LLM-based Automated Program Repair with Iterative Tree Search Research Papers Haichuan Hu Nanjing University of Science and Technology, Congqing He School of Computer Sciences, Universiti Sains Malaysia, Xiaochen Xie Department of Management, Zhejiang University, China, Hao Zhang School of Computer Sciences, Universiti Sains Malaysia, Quanjun Zhang School of Computer Science and Engineering, Nanjing University of Science and Technology | ||
12:20 10mTalk | Seeing is Fixing: Cross-Modal Reasoning with Multimodal LLMs for Visual Software Issue Repair Research Papers Kai Huang Technical University of Munich, Jian Zhang Nanyang Technological University, Xiaofei Xie Singapore Management University, Chunyang Chen TU Munich | ||