Hugging Face has released a new version of their Transformers Agents, a set of pre-trained models designed for multi-agent reinforcement learning tasks. The updated model, called Transformers Agents 2.0, includes several improvements over its predecessor. These enhancements include better performance on complex tasks and improved stability in training. The model's architecture is based on the popular Transformer-XL model. According to Hugging Face, the new version of the model has been tested on a range of benchmarks and shows promising results. --- Why it matters: This matters because it provides researchers with a more efficient and effective tool for developing multi-agent systems, which are increasingly important in areas such as robotics and autonomous vehicles. Source: https://huggingface.co/blog/agents