In this paper, we introduce a new agent-based method to build a decision-aid tool aimed to improve policy design. In our approach, a policy is defined as a set of levers, modelling the set of actions, the means to impact a complex system. Our method is generic, as it could be applied to any domain, and be coupled with any agent-based simulator. We could deal not only with simple levers (a single variable whose value is modified) but also complex ones (multiple variable modifications, qualitative effects, ...), unlike most optimization methods. It is based on the evolutionary algorithm CMA-ES, coupled with a normalized and aggregated fitness function. The fitness is normalized using estimated Ideal (best policy) and Nadir (worst policy) values, these values being dynamically computed during the execution of CMA-ES through a Pareto Front estimated with the ABM simulation. Moreover , to deal with complex levers, we introduce the FSM-branching algorithm, where a Finite State Machine (FSM) determines whether a complex policy can potentially be improved or has to be aborted. We tested our method with Economic Policies on the French Labor Market (FLM), allowing the modification of multiple elements of the FLM, and we compared the results to the reference, the FLM without any policy applied. The policies studied here comprise simple and complex levers. This experience shows the viability of our approach, the efficiency of our algorithms and illustrates how this combination of evolutionary optimization, multi-criteria aggregation and agent-based simulation could help any policy-maker to design better policies.