English
Related papers

Related papers: Pull Requests as a Training Signal for Repo-Level …

200 papers

Enabled by the pull-based development model, developers can easily contribute to a project through pull requests (PRs). When creating a PR, developers can add a free-form description to describe what changes are made in this PR and/or why.…

Software Engineering · Computer Science 2019-09-17 Zhongxin Liu , Xin Xia , Christoph Treude , David Lo , Shanping Li

Autonomous coding agents are reshaping software development by creating pull requests (PRs) on GitHub, referred to as agentic PRs. In parallel, the review process is also becoming autonomous, thereby making reviewer bots key actors in the…

Software Engineering · Computer Science 2026-04-28 Syeda Kaneez Fatima , Yousuf Abrar , Abdul Rehman Tahir , Amelia Nawaz , Shamsa Abid , Abdul Ali Bangash

Software developers often struggle to update APIs, leading to manual, time-consuming, and error-prone processes. We introduce MELT, a new approach that generates lightweight API migration rules directly from pull requests in popular library…

Software Engineering · Computer Science 2024-07-10 Daniel Ramos , Hailie Mitchell , Inês Lynce , Vasco Manquinho , Ruben Martins , Claire Le Goues

Autonomous coding agents increasingly contribute to software development by submitting pull requests on GitHub; yet, little is known about how these contributions integrate into human-driven review workflows. We present a large empirical…

Software Engineering · Computer Science 2026-02-24 Costain Nachuma , Minhaz Zibran

Small language models (SLMs) offer compelling advantages in cost, latency, and adaptability, but have so far lagged behind larger models on long-horizon software engineering tasks such as SWE-bench, where they suffer from pervasive action…

Software Engineering · Computer Science 2026-02-26 Patrick Tser Jern Kon , Archana Pradeep , Ang Chen , Alexander P. Ellis , Warren Hunt , Zijian Wang , John Yang , Samuel Thompson

Large Language Models (LLMs) have achieved impressive results on static code-generation benchmarks, but real-world software development unfolds as a continuous stream of evolving issues, fixes, and feature requests. We introduce…

Machine Learning · Computer Science 2025-07-02 Thomas Joshi , Shayan Chowdhury , Fatih Uysal

Executable software engineering data is valuable for training SWE agents, but scaling it remains difficult for two reasons: only a small fraction of real repository changes yield verifiable, high-signal task instances, and naively building…

Software Engineering · Computer Science 2026-03-24 Jiarong Liang , Zhiheng Lyu , Zijie Liu , Xiangchao Chen , Ping Nie , Kai Zou , Wenhu Chen

Pull request (PR) review is essential for ensuring software quality, yet automating this task remains challenging due to noisy supervision, limited contextual understanding, and inadequate evaluation metrics. We present Sphinx, a unified…

Software Engineering · Computer Science 2026-01-09 Daoan Zhang , Shuo Zhang , Zijian Jin , Jiebo Luo , Shengyu Fu , Elsie Nallipogu

In dynamic Industrial Internet of Things (IIoT) environments, models need the ability to selectively forget outdated or erroneous knowledge. However, existing methods typically rely on retain data to constrain model behavior, which…

Machine Learning · Computer Science 2025-11-13 Jiao Chen , Weihua Li , Jianhua Tang

Large language model (LLM)-based coding agents achieve impressive results on controlled benchmarks yet routinely produce pull requests that real maintainers reject. The root cause is not functional incorrectness but a lack of organicity:…

Software Engineering · Computer Science 2026-03-30 Mo Li , L. H. Xu , Qitai Tan , Ting Cao , Yunxin Liu

Research on applications of reinforcement learning (RL) to large language models has mostly been focused on single-turn problems, such as mathematical reasoning or single-shot code generation. While these problems can be viewed as…

In this technical report, we present SWE-Master, an open-source and fully reproducible post-training framework for building effective software engineering agents. SWE-Master systematically explores the complete agent development pipeline,…

Prior works on training software engineering agents have explored utilizing existing resources such as issues on GitHub repositories to construct software engineering tasks and corresponding test suites. These approaches face two key…

Software Engineering · Computer Science 2026-01-13 Yiqi Zhu , Apurva Gandhi , Graham Neubig

Retrieving the correct set of files from a large codebase is a crucial step in Automated Program Repair (APR). High recall is necessary to ensure that the relevant files are included, but simply increasing the number of retrieved files…

Software Engineering · Computer Science 2026-04-14 Mahir Labib Dihan , Faria Binta Awal , Md. Ishrak Ahsan

Background: Pull-based development has shaped the practice of Modern Code Review (MCR), in which reviewers can contribute code improvements, such as refactorings, through comments and commits in Pull Requests (PRs). Past MCR studies…

Software Engineering · Computer Science 2021-08-26 Flávia Coelho , Nikolaos Tsantalis , Tiago Massoni , Everton L. G. Alves

AI coding agents are now submitting pull requests (PRs) to software projects, acting not just as assistants but as autonomous contributors. As these agentic contributions are rapidly increasing across real repositories, little is known…

Software Engineering · Computer Science 2026-01-22 Ramtin Ehsani , Sakshi Pathak , Shriya Rawal , Abdullah Al Mujahid , Mia Mohammad Imran , Preetha Chatterjee

With the rise of the pull request mechanism in software development, the quality of pull requests has gained more attention. Prior works focus on improving the quality of pull request descriptions and several approaches have been proposed…

Software Engineering · Computer Science 2022-08-09 Ivana Clairine Irsan , Ting Zhang , Ferdian Thung , David Lo , Lingxiao Jiang

Code review is central to software engineering education but hard to scale in capstone projects due to tight deadlines, uneven peer feedback, and limited prior experience. We investigate an LLM-as-reviewer integrated directly into GitHub…

Software Engineering · Computer Science 2026-04-28 Eduardo Oliveira , Michael Fu , Patanamon Thongtanunam , Sonsoles López-Pernas , Mohammed Saqr

Peer code review locates common coding rule violations and simple logical errors in the early phases of software development, and thus reduces overall cost. However, in GitHub, identifying an appropriate code reviewer for a pull request is…

Software Engineering · Computer Science 2018-07-10 Mohammad Masudur Rahman , Chanchal K. Roy , Jason A. Collins

AI coding agents can autonomously generate pull requests (PRs), yet little is known about how their contributions compare to those of humans. We analyze 33,596 agent-generated PRs (APRs) and 6,618 human PRs (HPRs) to compare code-change…

Software Engineering · Computer Science 2026-01-27 Dung Pham , Taher A. Ghaleb