I had thoughts along these lines, but I was thinking that in order to be effective the cells would need to be dynamically sized, and I didn't see an obviously good way to do it (although I since ran across http://en.wikipedia.org/wiki/Local_outlier_factor -- may be of some interest). I'll be curious to know how this turns out for you.
My bot with cell wasn't very effective, and was getting complicated to modify, so I started anew with a clean, modular architecture and a way of combining different strategies, each of which is pretty simple. That gets me an effecctiv enough bot with room for improvement - most of the ants just scatter by avoiding walking on frequently-visited squares, and those that are near food and hives attack.
Now that I have that, I can start adding some more complicated pathfinding strategies, some optimisation, etc. - macro cells will probably be useful again, for o...
Aichallenge.org has started their third AI contest this year: Ants.
I mentioned this in the open thread, and there was a discussion about possibly making one or more "official" LessWrong teams. D_Alex has offered a motivational prize. If this interests you, please discuss in the comments!