This paper considers the problem of finding
as many as possible, hopefully all, solutions of the general
(i.e., not necessarily monotone) variational inequality problem
(VIP). Based on global optimization reformulation of VIP, we
propose a hybrid evolutionary algorithm that incorporates local
search in promising regions. In order to prevent searching process
from returning to the already detected global or local solutions,
we employ the tunneling and hump-tunneling function techniques.
The proposed algorithm is tested on a set of test problems in the
MCPLIB library and numerical results indicate that it works well
in practice.