We propose a hybrid method integrating agent-based modeling and heuristic tree search to solve complex batch scheduling problems. Agent-based modeling describes the batch process and constructs a feasible schedule. To overcome myopic decisions of agents, the agent-based simulation is embedded into a heuristic search algorithm. The heuristic algorithm partially explores the solution space generated by the agent-based simulation. Because global information of the objective function value is used in the search algorithm, the schedule performance is improved. As an efficient scheduling algorithm, the hybrid method is applicable to large-scale complex industrial scheduling problems. Its performance is demonstrated by a complex case study from The Dow Chemical Company.