FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910058202267648 |
|---|---|
| author | Ma, Ruize Jiang, Yilei Zhang, Shilin Ma, Zheng Feng, Yi Ng, Vincent Wang, Zhi Yue, Xiangyu Li, Chuanyi Lu, Lewei |
| author_facet | Ma, Ruize Jiang, Yilei Zhang, Shilin Ma, Zheng Feng, Yi Ng, Vincent Wang, Zhi Yue, Xiangyu Li, Chuanyi Lu, Lewei |
| contents | Multimodal Automated Program Repair (MAPR) extends traditional program repair by requiring models to jointly reason over source code, textual issue descriptions, and visual artifacts such as GUI screenshots. While recent LLM-based repair systems have shown promising results, existing approaches face several limitations: rigid workflow pipelines restrict exploration during debugging, visual reasoning is often performed over full-page screenshots without localized grounding, and failed repair attempts are rarely transformed into reusable knowledge. To address these challenges, we propose FailureMem, a multimodal repair framework that integrates three key mechanisms: a hybrid workflow-agent architecture that balances structured localization with flexible reasoning, active perception tools that enable region-level visual grounding, and a Failure Memory Bank that converts past repair attempts into reusable guidance. Experiments on SWE-bench Multimodal demonstrate FailureMem improves the resolved rate over GUIRepair by 3.7%. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_17826 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair Ma, Ruize Jiang, Yilei Zhang, Shilin Ma, Zheng Feng, Yi Ng, Vincent Wang, Zhi Yue, Xiangyu Li, Chuanyi Lu, Lewei Software Engineering Artificial Intelligence Multimodal Automated Program Repair (MAPR) extends traditional program repair by requiring models to jointly reason over source code, textual issue descriptions, and visual artifacts such as GUI screenshots. While recent LLM-based repair systems have shown promising results, existing approaches face several limitations: rigid workflow pipelines restrict exploration during debugging, visual reasoning is often performed over full-page screenshots without localized grounding, and failed repair attempts are rarely transformed into reusable knowledge. To address these challenges, we propose FailureMem, a multimodal repair framework that integrates three key mechanisms: a hybrid workflow-agent architecture that balances structured localization with flexible reasoning, active perception tools that enable region-level visual grounding, and a Failure Memory Bank that converts past repair attempts into reusable guidance. Experiments on SWE-bench Multimodal demonstrate FailureMem improves the resolved rate over GUIRepair by 3.7%. |
| title | FailureMem: A Failure-Aware Multimodal Framework for Autonomous Software Repair |
| topic | Software Engineering Artificial Intelligence |
| url | https://arxiv.org/abs/2603.17826 |