The basic market model has been shown to use remarkably little information
when functioning at equilibrium. But as Saari and Simon (1978)
showed, if there were a mechanism that would take a General Equilibrium
economy (Arrow–Debreu) to an equilibrium, that mechanism would
require an infinite amount of information. Thus, the stability problem
was basically unsolvable in the context of the general equilibrium
model. To repeat, starting from individuals with standard preferences
and adding them up allows one to show that there is an equilibrium but
does not permit one to say that it is unique nor how it could be attained.