LHRLAB/Graph-R1

Graph-R1 lets language models reason over knowledge graphs using multi-turn interactions and reinforcement learning for better question answering

View on index · View in 3D Map

Related repos

• Builds knowledge graphs for agents
• Synthesizes data using knowledge graphs
• Reinforcement learning framework for language agents
• turns text into knowledge graphs
• open-source reinforcement learning for language models
• Ask questions about a graph in natural language
• Converts text into knowledge graphs
• Graph native agentic system
• reinforcement learning library for training large language models, supports many RL algorithms, integrates with LLM tools, scales to models with up to 671B parameters
• Executes reasoning paths in parallel with language models