CodeV: Issue Resolving with Visual Data
Linhao Zhang, Daoguang Zan, Quanshun Yang, Zhirong Huang, Dong Chen, Bo Shen, Tianyu Liu, Yongshun Gong
Abstract
Large Language Models (LLMs) have advanced rapidly in recent years, with their applications in software engineering expanding to more complex repository-level tasks. GitHub issue resolving is a key challenge among these tasks. While recent approaches have made progress on this task, they focus on textual data within issues, neglecting visual data. However, this visual data is crucial for resolving issues as it conveys additional knowledge that text alone cannot. We propose CodeV, the first approach to leveraging visual data to enhance the issue-resolving capabilities of LLMs. CodeV resolves each issue by following a two-phase process: data processing and patch generation. To evaluate CodeV, we construct a benchmark for visual issue resolving, namely Visual SWE-bench. Through extensive experiments, we demonstrate the effectiveness of CodeV, as well as provide valuable insights into leveraging visual data to resolve GitHub issues.
BibTeX
@inproceedings{zhang-etal-2025-codev,
title = "{C}ode{V}: Issue Resolving with Visual Data",
author = "Zhang, Linhao and
Zan, Daoguang and
Yang, Quanshun and
Huang, Zhirong and
Chen, Dong and
Shen, Bo and
Liu, Tianyu and
Gong, Yongshun and
Pengjie, Huang and
Lu, Xudong and
Liang, Guangtai and
Cui, Lizhen and
Wang, Qianxiang",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.384/",
doi = "10.18653/v1/2025.findings-acl.384",
pages = "7350--7361",
ISBN = "979-8-89176-256-5"
}