Building design optimization (BDO) provides an approach for decreasing global energy consumption and achieving the goal of carbon neutrality. However, energy efficiency and comfort performance are two conflicting objectives when making optimal building design schemes. This study proposes a surrogate model-based multiple-objective optimization framework to balance the conflicting objectives and obtain an optimal design scheme for buildings. Firstly, an energy simulation model for generating energy consumption and design parameters is constructed, and the obtained data are utilized to train the surrogate model with the random forest (RF) algorithm. Then, multi-objective optimization algorithms are employed to generate a set of alternative plans for building schemes and determine the optimal building design solutions that can equilibrate the requirements for both energy conservation and building comfort. To verify the proposed optimization method in this paper, a residential building in Suzhou was selected as a case study. The study considered 10 building design parameters that are related to energy efficiency and thermal comfort. The results indicate that the RF surrogate model accurately predicts energy consumption, with a predicted MSE of 0.00012 and R2 of 0.99. In evaluating the Pareto set size, Pareto solution diversity, Pareto front proximity, and best solution quality, NSGA-II proved to be the most effective optimization algorithm for BDO problems. The final optimal solution of design parameters obtained by NSGA-II obviously improves the building performance of comfort and energy efficiency, and the results of the performance evaluation for different optimization algorithms provide guidance to make decisions on suitable algorithms and hyperparameter settings based on the greatest preference of the performance criteria. This study will help determine the best design options for buildings to achieve better energy efficiency in sustainable development and provide reference for similar projects. Practical applications This research makes valuable contributions in the following aspects:(a) It establishes a multi-objective optimization design model for a virtual building environment. This enables the visualization and digitization of the building model and further facilitates the transformation of the optimization model, thereby providing users with convenient decision-making tools; (b) The study provides designers and other stakeholders with comprehensive simulation-based analysis results and optimization techniques. These tools aid in making energy-saving multi-objective optimization decisions;(c) The research compares various optimization algorithms and presents their strengths and limitations, which will help designers select suitable algorithms based on practical requirements.