Cover Image

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Wei, Yuxiang, Duchenne, Olivier, Copet, Jade, Carbonneaux, Quentin, Zhang, Lingming, Fried, Daniel, Synnaeve, Gabriel, Singh, Rishabh, Wang, Sida I.
Format:	Preprint
Published:	2025
Subjects:	Software Engineering Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Toward Training Superintelligent Software Agents through Self-Play SWE-RL
by: Wei, Yuxiang, et al.
Published: (2025)

RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning
by: Gehring, Jonas, et al.
Published: (2024)

SWE-Replay: Efficient Test-Time Scaling for Software Engineering Agents
by: Ding, Yifeng, et al.
Published: (2026)

Live-SWE-agent: Can Software Engineering Agents Self-Evolve on the Fly?
by: Xia, Chunqiu Steven, et al.
Published: (2025)

SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains?
by: Yang, John, et al.
Published: (2024)

CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution
by: Gu, Alex, et al.
Published: (2024)

SWE-Shepherd: Advancing PRMs for Reinforcing Code Agents
by: Dihan, Mahir Labib, et al.
Published: (2026)

Practical Program Repair in the Era of Large Pre-trained Language Models
by: Xia, Chunqiu Steven, et al.
Published: (2022)

TestGenEval: A Real World Unit Test Generation and Test Completion Benchmark
by: Jain, Kush, et al.
Published: (2024)

Agentless: Demystifying LLM-based Software Engineering Agents
by: Xia, Chunqiu Steven, et al.
Published: (2024)

CWM: An Open-Weights LLM for Research on Code Generation with World Models
by: FAIR CodeGen team, et al.
Published: (2025)

Lingma SWE-GPT: An Open Development-Process-Centric Language Model for Automated Software Improvement
by: Ma, Yingwei, et al.
Published: (2024)

Training Software Engineering Agents and Verifiers with SWE-Gym
by: Pan, Jiayi, et al.
Published: (2024)

SWE-MiniSandbox: Container-Free Reinforcement Learning for Building Software Engineering Agents
by: Yuan, Danlong, et al.
Published: (2026)

From SWE-ZERO to SWE-HERO: Execution-free to Execution-based Fine-tuning for Software Engineering Agents
by: Ludwig, Nikolai, et al.
Published: (2026)

SWE-Bench++: A Framework for the Scalable Generation of Software Engineering Benchmarks from Open-Source Repositories
by: Wang, Lilin, et al.
Published: (2025)

SWE-Sharp-Bench: A Reproducible Benchmark for C# Software Engineering Tasks
by: Mhatre, Sanket, et al.
Published: (2025)

TOM-SWE: User Mental Modeling For Software Engineering Agents
by: Zhou, Xuhui, et al.
Published: (2025)

SWE-Exp: Experience-Driven Software Issue Resolution
by: Chen, Silin, et al.
Published: (2025)

SWE-smith: Scaling Data for Software Engineering Agents
by: Yang, John, et al.
Published: (2025)

Software Frugality in an Accelerating World: the Case of Continuous Integration
by: Perez, Quentin, et al.
Published: (2024)

SWE-Next: Scalable Real-World Software Engineering Tasks for Agents
by: Liang, Jiarong, et al.
Published: (2026)

SWE-Arena: An Interactive Platform for Evaluating Foundation Models in Software Engineering
by: Zhao, Zhimin
Published: (2025)

SWE-World: Building Software Engineering Agents in Docker-Free Environments
by: Sun, Shuang, et al.
Published: (2026)

SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development
by: Du, Yaxin, et al.
Published: (2025)

SWE-AGI: Benchmarking Specification-Driven Software Construction with MoonBit in the Era of Autonomous Agents
by: Zhang, Zhirui, et al.
Published: (2026)

SWE-Lego: Pushing the Limits of Supervised Fine-tuning for Software Issue Resolving
by: Tao, Chaofan, et al.
Published: (2026)

SWE-Master: Unleashing the Potential of Software Engineering Agents via Post-Training
by: Song, Huatong, et al.
Published: (2026)

Less Training, More Repairing Please: Revisiting Automated Program Repair via Zero-shot Learning
by: Xia, Chunqiu Steven, et al.
Published: (2022)

SWE-Debate: Competitive Multi-Agent Debate for Software Issue Resolution
by: Li, Han, et al.
Published: (2025)

SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
by: Badertdinov, Ibragim, et al.
Published: (2025)

SWE-Hub: A Unified Production System for Scalable, Executable Software Engineering Tasks
by: Zeng, Yucheng, et al.
Published: (2026)

A Vision on Open Science for the Evolution of Software Engineering Research and Practice
by: OliveiraJr, Edson, et al.
Published: (2024)

Magicoder: Empowering Code Generation with OSS-Instruct
by: Wei, Yuxiang, et al.
Published: (2023)

daVinci-Env: Open SWE Environment Synthesis at Scale
by: Fu, Dayuan, et al.
Published: (2026)

GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents
by: Shetty, Manish, et al.
Published: (2025)

R2E-Gym: Procedural Environments and Hybrid Verifiers for Scaling Open-Weights SWE Agents
by: Jain, Naman, et al.
Published: (2025)

Multitask-based Evaluation of Open-Source LLM on Software Vulnerability
by: Yin, Xin, et al.
Published: (2024)

SWE-WebDevBench: Evaluating Coding Agent Application Platforms as Virtual Software Agencies
by: Saxena, Siddhant, et al.
Published: (2026)

SWE-Effi: Re-Evaluating Software AI Agent System Effectiveness Under Resource Constraints
by: Fan, Zhiyu, et al.
Published: (2025)