Gaia Agent Evaluation Runner

Instructions:

  1. This app runs the GaiaAgent, a ReAct agent built with LangGraph.
  2. Log in to your Hugging Face account using the button below. This uses your HF username for submission.
  3. Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.

Agent Information:

  • Model: Uses OpenAI/Local LLM as configured in .env.
  • Tools: Web Search (DuckDuckGo), Python Execution, Calculator, File Operations, and RAG.
  • Architecture: LangGraph ReAct Agent.

Questions and Agent Answers

Questions and Agent Answers