balrog-ai/BALROG

Benchmark for agentic LLM and VLM reasoning on games

View on index · View in 3D Map

Related repos

• Implementations of 17+ agentic architectures
• Benchmark for cross-platform embodied agents
• Discovers tools for autonomous agents
• Benchmark evaluates LLMs as agents
• evaluate and track LLM experiments and AI agents
• Persistent memory for AI agents
• GenAI agent tutorials and code for building and experimenting with different AI agent techniques
• Evaluates agents in video games
• AI agents for internet research and task execution
• Memory layer for autonomous agents