4 papers
Trace-to-Architecture: Capability Bottleneck Diagnosis for Harness Revision
Wenfeng Wang, Jianrui Shi, Mingang Guo +5
Improving an LLM agent requires knowing what to change when it fails. Similar failures can require different fixes, and resolving one problem can expose another. We introduce Trace…
Empirical Evaluation of Large Language Models in Automated Program Repair
Jiajun Sun, Fengjie Li, Xinzhu Qi +2
The increasing prevalence of software bugs has made automated program repair (APR) a key research focus. Large language models (LLMs) offer new opportunities for APR, but existing…
Evaluating the Generalizability of LLMs in Automated Program Repair
Fengjie Li, Jiajun Jiang, Jiajun Sun +1
LLM-based automated program repair methods have attracted significant attention for their state-of-the-art performance. However, they were primarily evaluated on a few well known d…
Hybrid Automated Program Repair by Combining Large Language Models and Program Analysis
Fengjie Li, Jiajun Jiang, Jiajun Sun +1
Automated Program Repair (APR) has garnered significant attention due to its potential to streamline the bug repair process for human developers. Recently, LLM-based APR methods ha…