Continual-Intelligence/SEAL

Trains language models to generate self-edits via reinforcement learning

View on index · View in 3D Map

Related repos

• Code for large-scale depth-recurrent language model training
• open-source reinforcement learning for language models
• Framework for self-evolving autonomous language agents
• Reinforcement learning framework for language agents
• lets agents remember and learn from past chats
• Reinforcement learning toolkit for text generation on MLX
• Reinforcement learning for agentic search without external engines
• Framework for AI agents with self-learning capabilities
• AI agent that learns, automates tasks, and builds its own tools
• framework for building and deploying stateful AI agents