Multistate searching methods are a subfield of distributed artificial intelligence that aims to provide both principles for construction of complex systems involving multiple states and mechanisms for coordination of independent agents' actions. This paper proposes a multistate searching algorithm with reinforcement learning for the automatic core design of a boiling water reactor. The characteristics of this algorithm are that the coupling structure and the coupling operation suitable for the assigned problem are assumed and an optimal solution is obtained by mutual interference in multistate transitions using multiagents. Calculations in an actual plant confirmed that the proposed algorithm increased the convergence ability of the optimization process.