Publication Type

Conference Proceeding Article

Version

publishedVersion

Publication Date

4-2026

Abstract

Patch backporting is crucial and prevalent in the maintenance of modern open-source software such as Linux kernels and forked repositories. However, porting patches across program versions remains a challenging problem due to the complexity of synergizing diverse patches with divergent program versions. In this paper, we propose PatchGPT, an agentic patch backporting framework for fine-grained patch generation. PatchGPT encompasses three agents: Miner for decomposing a sequence of atomic change steps as the original patch plan, Adapter for adapting the patch plan, and Executor for executing the adapted patch plan according to predefined change semantics. We conduct experiments on the PPatHF’s benchmark containing 310 Vim-NeoVim patch pairs. The experiment results indicate that PatchGPT not only achieves a success rate of up to 50.96%, outperforming PPatHF by 8.71%, but also provides actionable insights into the reasoning process behind patch generation and adaptation.

Keywords

Large language model, Patch backport

Discipline

Artificial Intelligence and Robotics | Software Engineering

Research Areas

Intelligent Systems and Optimization

Areas of Excellence

Digital transformation

Publication

FORGE '26: Proceedings of the 2026 IEEE/ACM Third International Conference on AI Foundation Models and Software Engineering, Rio de Janeiro, Brazil, April 12-13

First Page

155

Last Page

159

ISBN

9798400724770

Identifier

10.1145/3793655.3793723

Publisher

ACM

City or Country

New York

Additional URL

https://doi.org/10.1145/3793655.3793723

Download

Share

COinS