Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2510.22396 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915576989876224 |
|---|---|
| author | Li, Zhaoyang Yu, Zheng Song, Jingyi Xu, Meng Luo, Yuxuan Mu, Dongliang |
| author_facet | Li, Zhaoyang Yu, Zheng Song, Jingyi Xu, Meng Luo, Yuxuan Mu, Dongliang |
| contents | Patch backporting, the process of migrating mainline security patches to older branches, is an essential task in maintaining popular open-source projects (e.g., Linux kernel). However, manual backporting can be labor-intensive, while existing automated methods, which heavily rely on predefined syntax or semantic rules, often lack agility for complex patches.
In this paper, we introduce PORTGPT, an LLM-agent for end-to-end automation of patch backporting in real-world scenarios. PORTGPT enhances an LLM with tools to access code on-demand, summarize Git history, and revise patches autonomously based on feedback (e.g., from compilers), hence, simulating human-like reasoning and verification. PORTGPT achieved an 89.15% success rate on existing datasets (1815 cases), and 62.33% on our own dataset of 146 complex cases, both outperforms state-of-the-art of backporting tools. We contributed 9 backported patches from PORTGPT to the Linux kernel community and all patches are now merged. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_22396 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PortGPT: Towards Automated Backporting Using Large Language Models Li, Zhaoyang Yu, Zheng Song, Jingyi Xu, Meng Luo, Yuxuan Mu, Dongliang Cryptography and Security Patch backporting, the process of migrating mainline security patches to older branches, is an essential task in maintaining popular open-source projects (e.g., Linux kernel). However, manual backporting can be labor-intensive, while existing automated methods, which heavily rely on predefined syntax or semantic rules, often lack agility for complex patches. In this paper, we introduce PORTGPT, an LLM-agent for end-to-end automation of patch backporting in real-world scenarios. PORTGPT enhances an LLM with tools to access code on-demand, summarize Git history, and revise patches autonomously based on feedback (e.g., from compilers), hence, simulating human-like reasoning and verification. PORTGPT achieved an 89.15% success rate on existing datasets (1815 cases), and 62.33% on our own dataset of 146 complex cases, both outperforms state-of-the-art of backporting tools. We contributed 9 backported patches from PORTGPT to the Linux kernel community and all patches are now merged. |
| title | PortGPT: Towards Automated Backporting Using Large Language Models |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2510.22396 |