TCSE logo 
 Sigsoft logo
Sustainability badge
Tue 29 Apr 2025 16:20 - 16:40 at 210 - APR Session 4 Chair(s): Tegawendé F. Bissyandé, Chao Peng

Automated program repair is designed to automate the process of bug-fixing. In recent years, thanks to the rapid development of large language models (LLMs), automated repair has achieved remarkable progress. Advanced APR techniques powered by conversational LLMs, most notably ChatGPT, have exhibited impressive repair abilities and gained increasing popularity due to the capabilities of the underlying LLMs in providing repair feedback and performing iterative patch improvement. Despite the superiority, conversational APR techniques can still fail to repair a large number of bugs. For example, a state-of-the-art conversational technique CHATREPAIR does not correctly repair over half of the single-function bugs in the Defects4J dataset. To understand the effectiveness and failures of conversational LLM-based repair and provide possible directions for improvement, we studied the exemplary CHATREPAIR with a focus on comparing the effectiveness of its cloze-style and full-function repair strategies, assessing its key iterative component for patch improvement, and analyzing the repair failures. Our study has led to a series of findings, which we believe provide key implications for future research.

Tue 29 Apr

Displayed time zone: Eastern Time (US & Canada) change

16:00 - 17:30
APR Session 4APR at 210
Chair(s): Tegawendé F. Bissyandé University of Luxembourg, Chao Peng ByteDance
16:00
20m
Talk
Simple Fault Localization using Execution Traces
APR
Julian Prenner Free University of Bozen-Bolzano, Romain Robbes CNRS, LaBRI, University of Bordeaux
16:20
20m
Talk
Studying and Understanding the Effectiveness and Failures of Conversational LLM-Based Repair
APR
Aolin Chen Wuhan University, Haojun Wu Wuhan University, Qi Xin Wuhan University, Steven P. Reiss Brown University, Jifeng Xuan Wuhan University
16:40
20m
Talk
Towards Unveiling Vulnerability Remediation Tactics from OSS Community
APR
Lyuye Zhang Nanyang Technological University, Wu Jiahui , Chengwei Liu Nanyang Technological University, Kaixuan Li East China Normal University, Sen Chen Nankai University, Yang Liu Nanyang Technological University
17:00
20m
Talk
Which Inputs Trigger my Patch?
APR
Martin Eberlein Humboldt-Universtität zu Berlin, Moeketsi Raselimo Humboldt-Universität zu Berlin, Germany and Stellenbosch University, South Africa, Lars Grunske Humboldt-Universität zu Berlin
:
:
:
: