OpenClaw-RL: Train any agent simply by talking
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!
Solve Visual Understanding with Reinforced VLMs
Robust recipes to align language models with human and AI preferences