When training multilingual models a common problem is language mixing or code switching, in which models may respond in multiple languages when we would expect them to use just one. This can also happen in reasoning models, such as DeepSeek-R1. In their paper, they found that

Sometimes when reading books it can be hard to get a grasp for a problem in practice. This video popped up on IG showcasing one of the important principles of multi-agent systems.

With “agents” the hot topic of 2025, we should take a step back and ask ourselves, why do we want autonomous software? Let’s explore some reasons we’d want agents making decisions themselves.

“We will update our paper list every two weeks and include all the following papers in the next version of our paper. Please Feel free to contact me in case we have missed any papers!” - (Guo et al., 2024)

Games are fun. Humans love watching a variety of them from NFL to League of Legends to Mahjong. The competitive nature of games is enticing and the infinite strategies help keep them fresh. These factors also make them great testing grounds for AI. For example, recent work from the same group behind the ARC-AGI challenge pits LLMs against each other in games of snake to find out which is the best. In this article, let’s discuss their findings along with other work towards using competitive games to evaluate AI.