Image de couverture de livre

RepoForge: Training a SOTA Fast-thinking SWE Agent with an End-to-End Data Curation Pipeline Synergizing SFT and RL at Scale

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Chen, Zhilong, Zhao, Chengzong, Chen, Boyuan, Lin, Dayi, Chen, Yihao, Leung, Arthur, Rajbahadur, Gopi Krishnan, Oliva, Gustavo A., Zhang, Haoxiang, Bhatia, Aaditya, Yong, Chong Chun, Hassan, Ahmed E.
Format:	Preprint
Publié:	2025
Sujets:	Software Engineering
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

SPICE: An Automated SWE-Bench Labeling Pipeline for Issue Clarity, Test Coverage, and Effort Estimation
par: Oliva, Gustavo A., et autres
Publié: (2025)

Data Quality Antipatterns for Software Analytics
par: Bhatia, Aaditya, et autres
Publié: (2024)

Rethinking Software Engineering in the Foundation Model Era: A Curated Catalogue of Challenges in the Development of Trustworthy FMware
par: Hassan, Ahmed E., et autres
Publié: (2024)

SimClone: Detecting Tabular Data Clones using Value Similarity
par: Yang, Xu, et autres
Publié: (2024)

Edit, But Verify: An Empirical Audit of Instructed Code-Editing Benchmarks
par: Ebrahimi, Amir M., et autres
Publié: (2026)

From Cool Demos to Production-Ready FMware: Core Challenges and a Technology Roadmap
par: Rajbahadur, Gopi Krishnan, et autres
Publié: (2024)

Keeping Deep Learning Models in Check: A History-Based Approach to Mitigate Overfitting
par: Li, Hao, et autres
Publié: (2024)

Studying the Impact of TensorFlow and PyTorch Bindings on Machine Learning Software Quality
par: Li, Hao, et autres
Publié: (2024)

SWE-Effi: Re-Evaluating Software AI Agent System Effectiveness Under Resource Constraints
par: Fan, Zhiyu, et autres
Publié: (2025)

RepoGenesis: Benchmarking End-to-End Microservice Generation from Readme to Repository
par: Peng, Zhiyuan, et autres
Publié: (2026)

PromptExp: Multi-granularity Prompt Explanation of Large Language Models
par: Dong, Ximing, et autres
Publié: (2024)

Implementing AI Bill of Materials (AI BOM) with SPDX 3.0: A Comprehensive Guide to Creating AI and Dataset Bill of Materials
par: Bennet, Karen, et autres
Publié: (2025)

RIG: Synergizing Reasoning and Imagination in End-to-End Generalist Policy
par: Zhao, Zhonghan, et autres
Publié: (2025)

SWE-Spot: Building Small Repo-Experts with Repository-Centric Learning
par: Peng, Jinjun, et autres
Publié: (2026)

BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing?
par: Chen, Guoxin, et autres
Publié: (2026)

ChronoForge-RL: Chronological Forging through Reinforcement Learning for Enhanced Video Understanding
par: Chen, Kehua
Publié: (2025)

From Hugging Face to GitHub: Tracing License Drift in the Open-Source AI Ecosystem
par: Jewitt, James, et autres
Publié: (2025)

Permissive-Washing in the Open AI Supply Chain: A Large-Scale Audit of License Integrity
par: Jewitt, James, et autres
Publié: (2026)

From Representational Complementarity to Dual Systems: Synergizing VLM and Vision-Only Backbones for End-to-End Driving
par: Ang, Sining, et autres
Publié: (2026)

Generalizable End-to-End Tool-Use RL with Synthetic CodeGym
par: Du, Weihua, et autres
Publié: (2025)

The Hitchhikers Guide to Production-ready Trustworthy Foundation Model powered Software (FMware)
par: Vasilevski, Kirill, et autres
Publié: (2025)

QiMeng-Attention: SOTA Attention Operator is generated by SOTA Attention Algorithm
par: Zhou, Qirui, et autres
Publié: (2025)

EgoPush: Learning End-to-End Egocentric Multi-Object Rearrangement for Mobile Robots
par: An, Boyuan, et autres
Publié: (2026)

Model Context Protocol (MCP) Tool Descriptions Are Smelly! Towards Improving AI Agent Efficiency with Augmented MCP Tool Descriptions
par: Hasan, Mohammed Mehedi, et autres
Publié: (2026)

End-to-End Reinforcement Learning of Curative Curtailment with Partial Measurement Availability
par: Wolf, Hinrikus, et autres
Publié: (2024)

EndToEndML: An Open-Source End-to-End Pipeline for Machine Learning Applications
par: Pillai, Nisha, et autres
Publié: (2024)

An End-to-End Real-World Camera Imaging Pipeline
par: Xu, Kepeng, et autres
Publié: (2024)

Achieving the Safety and Security of the End-to-End AV Pipeline
par: Curran, Noah T., et autres
Publié: (2024)

AlphaForgeBench: Benchmarking End-to-End Trading Strategy Design with Large Language Models
par: Zhang, Wentao, et autres
Publié: (2026)

From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection
par: Li, Youpeng, et autres
Publié: (2026)

End-to-End Data Engineering Pipeline for E-Commerce Analytics
par: Kadavala, Priyanka Raju
Publié: (2025)

An End-to-End Depth-Based Pipeline for Selfie Image Rectification
par: Alhawwary, Ahmed, et autres
Publié: (2024)

A Framework for Cryptographic Verifiability of End-to-End AI Pipelines
par: Balan, Kar, et autres
Publié: (2025)

Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL
par: Wang, Sudong, et autres
Publié: (2026)

Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers
par: Hasan, Mohammed Mehedi, et autres
Publié: (2025)

An Empirical Study of Testing Practices in Open Source AI Agent Frameworks and Agentic Applications
par: Hasan, Mohammed Mehedi, et autres
Publié: (2025)

Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning
par: Chen, Liang, et autres
Publié: (2025)

Hint-AD: Holistically Aligned Interpretability in End-to-End Autonomous Driving
par: Ding, Kairui, et autres
Publié: (2024)

StraightLine: An End-to-End Resource-Aware Scheduler for Machine Learning Application Requests
par: Ching, Cheng-Wei, et autres
Publié: (2024)

Understanding the Performance Behaviors of End-to-End Protein Design Pipelines on GPUs
par: Hwang, Jinwoo, et autres
Publié: (2026)