A co-evolutional immune algorithm for the optimization of a function with real parameters is described. It uses a cooperative co-evolution of two populations, one is a population of antibodies and the other is a population of successful mutation vectors. These two population evolve together to improve the diversity of the antibodies. The algorithm described is then tested on a suite of optimization problems. The results show that on most of test functions, this algorithm can converge to the global optimum at quicker rate in a given range, the performance of optimization is improved effetely.