Hugging Face and Adyen introduce DABStep, a benchmark of over 450 real-world data analysis tasks for evaluating LLM agents. Current models achieve only 16% accuracy.
π0 and π0-FAST, Vision-Language-Action models developed by Physical Intelligence, are now available in the Hugging Face LeRobot repository, enabling generalist robot control across 7 platforms and 68…
Hugging Face open-sourced an agentic framework for deep research, using a CodeAgent and the smolagents library, to reproduce OpenAI's Deep Research system.