Researchers have developed a framework for coordinating multiple interacting units in complex systems. The approach uses a large language model (LLM) to make decisions based on heterogeneous operational context and task-specific controllers or optimizers generate executable actions. The method also evaluates the consequences of these decisions over time, rather than just their immediate outcome. This was tested on traffic control and energy management tasks, where it outperformed other methods. --- Why it matters: This research matters because it provides a new approach to coordinating complex systems, which is crucial in fields like transportation and energy management. The ability to evaluate the long-term consequences of decisions can lead to more efficient and effective control strategies. Source: https://arxiv.org/abs/2608.15041