Cornell scientists have applied genetic programming to experimental data in order to elicit fundamental physical laws governing the data.  These physical laws include Lagrangians and laws relating to momentum conservation.  The article is available here.  This is a triumph for genetic computing.  If one imagines the evolution of scientific discovery in human lifetime terms, the ability to speed this process via evolutionary simulation is quite interesting.  However, these types of algorithms can never replace human inspiration and creativity in developing theoretical models.