activity
20242026
collaborators

6 papers

cs.SE2026

On the Effectiveness of Code Representation in Deep Learning-Based Automated Patch Correctness Assessment

Quanjun Zhang, Haichuan Hu, Chunrong Fang +5

Automated program repair (APR) attempts to generate correct patches and has drawn wide attention from both academia and industry in the past decades. However, APR is continuously s…

cs.CL2026

Red Skills or Blue Skills? A Dive Into Skills Published on ClawHub

Haichuan Hu, Ye Shang, Quanjun Zhang

Skill ecosystems have emerged as an increasingly important layer in Large Language Model (LLM) agent systems, enabling reusable task packaging, public distribution, and community-d…

cs.SE2026

CL4SE: Benchmarking Context Learning on Software Engineering

Haichuan Hu, Quanjun Zhang, Ye Shang +4

Context engineering has emerged as a pivotal paradigm for unlocking the potential of Large Language Models (LLMs) in Software Engineering (SE) tasks, enabling performance gains at…

cs.SE2026

ComPass: Contrastive Learning for Automated Patch Correctness Assessment in Program Repair

Quanjun Zhang, Ye Shang, Haichuan Hu +3

Automated program repair (APR) attempts to reduce manual debugging efforts and plays a vital role in software maintenance. Despite remarkable progress, APR is still limited in gene…

cs.SE2025

Repair-R1: Better Test Before Repair

Haichuan Hu, Xiaochen Xie, Quanjun Zhang

APR (Automated Program Repair) aims to automatically locate program defects, generate patches and validate the repairs. Existing techniques for APR are often combined with LLMs (La…

cs.SE2024

Can GPT-O1 Kill All Bugs? An Evaluation of GPT-Family LLMs on QuixBugs

Haichuan Hu, Ye Shang, Guolin Xu +2

LLMs have long demonstrated remarkable effectiveness in automatic program repair (APR), with OpenAI's ChatGPT being one of the most widely used models in this domain. Through conti…