This work introduces a new evolutionary approach to search for a global solution to multiobjective optimisation problem in the Pareto sense. Novelty of the proposed method consists in application of an evolutionary multi-agent system (EMAS) instead of classical evolutionary algorithms. Decentralisation of the evolution process in EMAS allows for intensive exploration of the search space and effective approximation of the whole Pareto frontier. In the paper the intended application of the proposed technique as a core of a decision support system for balancing of production lines is described.