Imagen de Portada

SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Xie, Chengxing, Li, Bowen, Gao, Chang, Du, He, Lam, Wai, Zou, Difan, Chen, Kai
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

SWE-bench-java: A GitHub Issue Resolving Benchmark for Java
por: Zan, Daoguang, et al.
Publicado: (2024)

Emoji Promotes Developer Participation and Issue Resolution on GitHub
por: Zhou, Yuhang, et al.
Publicado: (2023)

SWE-bench: Can Language Models Resolve Real-World GitHub Issues?
por: Jimenez, Carlos E., et al.
Publicado: (2023)

Classifying Issues in Open-source GitHub Repositories
por: Raaj, Amir Hossain, et al.
Publicado: (2025)

LEAN-GitHub: Compiling GitHub LEAN repositories for a versatile LEAN prover
por: Wu, Zijian, et al.
Publicado: (2024)

How Complex is a GitHub Issue?
por: Anonymous
Publicado: (2025)

Mapping GitHub Sponsorships: A Longitudinal Observatory for Open-Source Sustainability
por: Hiltz, Rylan, et al.
Publicado: (2026)

On Categorizing Open Source Software Security Vulnerability Reporting Mechanisms on GitHub
por: Kancharoendee, Sushawapak, et al.
Publicado: (2025)

Engineering Students' Usage and Perceptions of GitHub Copilot in Open-Source Projects
por: Rani, Neha, et al.
Publicado: (2026)

A Human-Like Reasoning Framework for Multi-Phases Planning Task with Large Language Models
por: Xie, Chengxing, et al.
Publicado: (2024)

Imago GitHub training
por: Elsey, Jonathan
Publicado: (2026)

GitHub Proxy Server: A tool for supporting massive data collection on GitHub
por: Borges, Hudson Silva, et al.
Publicado: (2025)

OmniGIRL: A Multilingual and Multimodal Benchmark for GitHub Issue Resolution
por: Guo, Lianghong, et al.
Publicado: (2025)

MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
por: Tao, Wei, et al.
Publicado: (2024)

Incivility in Open Source Projects: A Comprehensive Annotated Dataset of Locked GitHub Issue Threads
por: Ehsani, Ramtin, et al.
Publicado: (2024)

Visual Analysis of GitHub Issues to Gain Insights
por: Proma, Rifat Ara, et al.
Publicado: (2024)

Characterizing the Failure Modes of LLMs in Resolving Real-World GitHub Issues
por: Jiang, Yanjie, et al.
Publicado: (2026)

METXico Innovation CODE GitHub
por: Xool-Tamayo, Jorge, et al.
Publicado: (2023)

Guidelines for Developing Bots for GitHub
por: Wessel, Mairieli, et al.
Publicado: (2022)

Prioritising GitHub Priority Labels
por: Caddy, James, et al.
Publicado: (2024)

"My GitHub Sponsors profile is live!" Investigating the Impact of Twitter/X Mentions on GitHub Sponsors
por: Fan, Youmei, et al.
Publicado: (2024)

From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem
por: Jewitt, James, et al.
Publicado: (2025)

Can GitHub Issues Help in App Review Classifications?
por: Abedini, Yasaman, et al.
Publicado: (2023)

What Makes a GitHub Issue Ready for Copilot?
por: Sayagh, Mohammed
Publicado: (2025)

Automating the Detection of Code Vulnerabilities by Analyzing GitHub Issues
por: Cipollone, Daniele, et al.
Publicado: (2025)

What Drives Issue Resolution Speed? An Empirical Study of Scientific Workflow Systems on GitHub
por: Alam, Khairul, et al.
Publicado: (2025)

The Impact of Sanctions on GitHub Developers and Activities
por: Fan, Youmei, et al.
Publicado: (2024)

Fingerprinting AI Coding Agents on GitHub
por: Ghaleb, Taher A.
Publicado: (2026)

Social Media Reactions to Open Source Promotions: AI-Powered GitHub Projects on Hacker News
por: Meakpaiboonwattana, Prachnachai, et al.
Publicado: (2025)

The Impact of Generative AI on Collaborative Open-Source Software Development: Evidence from GitHub Copilot
por: Song, Fangchen, et al.
Publicado: (2024)

LLM-Enabled Open-Source Systems in the Wild: An Empirical Study of Vulnerabilities in GitHub Security Advisories
por: Shifat, Fariha Tanjim, et al.
Publicado: (2026)

Confidence as a Reward: Transforming LLMs into Reward Models
por: Du, He, et al.
Publicado: (2025)

An Empirical Study of ChatGPT-Related Projects and Their Issues on GitHub
por: Lin, Zheng, et al.
Publicado: (2024)

What Characteristics Make ChatGPT Effective for Software Issue Resolution? An Empirical Study of Task, Project, and Conversational Signals in GitHub Issues
por: Ehsani, Ramtin, et al.
Publicado: (2025)

Immersion in the GitHub Universe: Scaling Coding Agents to Mastery
por: Zhao, Jiale, et al.
Publicado: (2026)

Demystifying and Detecting Agentic Workflow Injection Vulnerabilities in GitHub Actions
por: Wang, Shenao, et al.
Publicado: (2026)

GitHub Marketplace for Automation and Innovation in Software Production
por: Saroar, SK Golam, et al.
Publicado: (2024)

Introducing Traceability in GitHub for Medical Software Development
por: Stirbu, Vlad, et al.
Publicado: (2021)

The Landscape of Toxicity: An Empirical Investigation of Toxicity on GitHub
por: Sarker, Jaydeb, et al.
Publicado: (2025)

Chaos Engineering in the Wild: Findings from GitHub
por: Owotogbe, Joshua, et al.
Publicado: (2025)