Hugging Face has added support for Vision-Language Models (VLMs) to its SmolAgents framework. SmolAgents is a lightweight, modular architecture designed for building and testing multi-agent systems. The inclusion of VLMs enables the integration of visual perception capabilities into these systems. This could have implications for applications such as robotics or autonomous vehicles. --- Why it matters: This matters because it allows researchers to explore more complex scenarios in AI, specifically those involving vision and language tasks. It may also enable the development of more efficient and effective multi-agent systems. Source: https://huggingface.co/blog/smolagents-can-see