Scientific and engineering problems often require a large amount of computing resources to conduct large-scale simulations with a wide range of input, parameters. This paper describes an application parameter meta service and agent-controlled loop scheduling for executing multiple parameter sweep applications in a distributed environment. The proposed system provides a flexible and practical environment for generating a large set of independent jobs and for scheduling them over distributed resources on the grid. Using the proposed environment, we conducted a protein folding experiment that had about four thousands initial data on the pacific rim applications and grid middleware assembly (PRAGMA) testbed. The folding optimization provided 3-dirnensional protein atomic structures.