Vibe Coding DiscoverAReaL
View on GitHubThe RL Bridge for LLM-based Agent Applications. Made Simple & Flexible.
AReaL is distributed infrastructure for asynchronous reinforcement learning of LLMs and agent applications. It includes training and inference services, multiple RL algorithms, and examples for reasoning, coding, search, and customer-service agents.
Use Cases
Train reasoning models with reinforcement learningTrain multi-turn LLM agentsRun asynchronous RL experiments across GPU clustersOptimize coding agents with end-to-end RLTrain search and customer-service agentsConnect existing agent applications to online RL training
Built With
- Language
- Python
- Frameworks
- PyTorch · Hugging Face Transformers · SGLang · vLLM · Ray · LangChain · OpenAI Agents SDK · Claude Agent SDK · OpenHands
Tags
reinforcement-learning · agentic-rl · LLM-training · asynchronous-training · distributed-training · reasoning-models · multi-turn-agents · online-RL