While new models with more parameters and better reasoning are valuable, models are still limited by their lack of working memory. Context windows and improved memory will drive the most innovation in agentic AI next year, by giving agents the persistent memory they need to learn from past actions and operate autonomously on complex, long-term goals. With these improvements, agents will move beyond the limitations of single interactions and provide continuous support.
In the study, they tracked 121 adults aged between 18 and 50 and split them into two groups. All underwent cardiovascular fitness tests and were quizzed about their lifestyle. Two days later, all participants then gave blood samples and had an electroencephalographic (EEG) scan to record the electrical activity of the brain. The first group then did sets of weight exercises of moderate difficulty, while the other was asked to watch a video of adults performing resistance exercises. The resistance exercises lasted for 42 minutes.