The research area is witnessing significant advancements in the development and evaluation of autonomous agents, particularly in the context of web interaction and building energy optimization. Innovations are focusing on creating standardized environments and frameworks that streamline the evaluation and benchmarking of these agents, thereby enhancing reproducibility and comparability. In the realm of web agents, there is a notable shift towards more efficient and scalable interaction methods, reducing computational overhead and improving performance on dynamic web interfaces. Meanwhile, in building energy optimization, the emphasis is on integrating machine learning, particularly reinforcement learning, with simulation tools to develop intelligent control strategies that balance energy efficiency with occupant comfort. These developments collectively aim to push the boundaries of autonomous systems, making them more adaptable and capable in real-world applications.