facebookresearch / swe-rlLinks
[NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"
☆602Updated 6 months ago
Alternatives and similar repositories for swe-rl
Users that are interested in swe-rl are comparing it to the libraries listed below
Sorting:
- Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]☆547Updated 2 months ago
- SkyRL: A Modular Full-stack RL Library for LLMs☆950Updated this week
- [NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents☆414Updated last week
- Official repository for the paper "LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code"☆670Updated 2 months ago
- [ICML 2025 Oral] CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction☆550Updated 5 months ago
- AWM: Agent Workflow Memory☆326Updated 8 months ago
- ☆1,273Updated 3 weeks ago
- Building Open LLM Web Agents with Self-Evolving Online Curriculum RL☆457Updated 4 months ago
- MLGym A New Framework and Benchmark for Advancing AI Research Agents☆557Updated last month
- Automatic evals for LLMs☆539Updated 3 months ago
- Code and implementations for the paper "AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcemen…☆409Updated 3 weeks ago
- AgentLab: An open-source framework for developing, testing, and benchmarking web agents on diverse tasks, designed for scalability and re…☆414Updated this week
- ☆275Updated 2 months ago
- A project to improve skills of large language models☆568Updated last week
- Meta Agents Research Environments is a comprehensive platform designed to evaluate AI agents in dynamic, realistic scenarios. Unlike stat…☆263Updated 2 weeks ago
- 🌾 OAT: A research-friendly framework for LLM online alignment, including reinforcement learning, preference learning, etc.☆472Updated 3 weeks ago
- ☆218Updated 2 weeks ago
- An agent benchmark with tasks in a simulated software company.☆556Updated 2 weeks ago
- [ICLR'25] BigCodeBench: Benchmarking Code Generation Towards AGI☆430Updated last month
- A MemAgent framework that can be extrapolated to 3.5M, along with a training framework for RL training of any agent workflow.☆703Updated 2 months ago
- Benchmark and research code for the paper SWEET-RL Training Multi-Turn LLM Agents onCollaborative Reasoning Tasks☆245Updated 5 months ago
- An Open-Source Large-Scale Reinforcement Learning Project for Search Agents☆442Updated last week
- Multi-SWE-bench: A Multilingual Benchmark for Issue Resolving☆258Updated this week
- MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering☆985Updated last week
- 🌍 Repository for "AppWorld: A Controllable World of Apps and People for Benchmarking Interactive Coding Agent", ACL'24 Best Resource Pap…☆250Updated last month
- ☆962Updated 8 months ago
- ☆815Updated last month
- Code for the paper: "Learning to Reason without External Rewards"☆357Updated 2 months ago
- Large Reasoning Models☆804Updated 10 months ago
- Open sourced predictions, execution logs, trajectories, and results from model inference + evaluation runs on the SWE-bench task.☆215Updated this week