A search party combs a foggy field. At first, people spread out wide: a high 'temperature' of search means a great variety of attempts. Upon finding a trace, they close in. But the speed of convergence is critical — narrow the circle too early, and the best find stays aside. The coordinator assesses the spread of searchers and commands when to speed up or slow down.

In robotics, such a coordinator is entropy — a measure of uncertainty and diversity. The algorithm generates hundreds of possible routes and measures their spread in real time. As long as the options are as colorful as a spectroscopy spectrum, cooling is accelerated. When the spread drops, the algorithm slows down to avoid getting stuck in a dead end — much like the search for dark matter: we don't see it but catch hints.