PortGPT: Towards Automated Backporting Using Large Language Models

2025-10-25

AI Summary

Backporting security patches to older open-source software versions remains largely manual, while existing automated approaches rely on rigid, syntactic rules that fail to handle complex, context-sensitive patch transformations. Method: This paper proposes an intelligent agent framework powered by large language models (LLMs), integrating on-demand code retrieval, Git history summarization, and compilation-feedback-driven autonomous correction to emulate human reasoning and validation in end-to-end patch backporting. Contribution/Results: The framework achieves superior semantic understanding and contextual adaptability compared to rule-based methods. Evaluated on 1,815 test cases, it attains an overall success rate of 89.15% and 62.33% on 146 challenging cases—significantly outperforming state-of-the-art tools. Moreover, nine generated patches have been accepted and merged into the Linux kernel mainline, demonstrating both technical efficacy and practical utility.

Technology Category

• Multiagent Systems: Teamwork
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

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.

Problem

• Automating security patch migration to older software branches
• Overcoming limitations of rigid rule-based backporting systems
• Handling complex patches requiring human-like reasoning capabilities

Innovation

• LLM-agent automates end-to-end patch backporting process
• Enhances LLM with code access and Git history tools
• Autonomously revises patches using compiler feedback mechanisms