Net-zero energy buildings (NZEB) have received widespread attention for their excellent energy and carbon reduction potential in various countries. However, relatively little research has been conducted on the life performance of its primary form: the ultra-low energy building (ULEB). This paper proposes an optimization method combining meta-models to investigate the carbon reduction potential of ultra-low energy buildings in severely cold regions of China. The XGBoost algorithm is used to construct a meta-model of building performance, and the grid search method is used to obtain a high-precision meta-model with an R² of 0.967. Secondly, NSGA-II is used to find passive technical solutions based on the meta-model that minimize the global warming potential (GWP), global cost (GC), and operation energy consumption (OE). Finally, the variables affecting the life-cycle performance of buildings were ranked by sensitivity analysis. The results show that GWP, GC, and OE are reduced by 12.7%, 6.7%, and 7.4% compared with the original building through the optimization process proposed. Sensitivity analysis showed that for GWP, the top four sensitivities are window type (TW) > WWR of south wall (WWRS) > roof insulation thickness (IR) > WWR of north wall (WWRN). For GC, the top four sensitivities are: TW > WWRS > IR > WWR of west wall (WWRW); for OE, the top four sensitivities are: TW > IR > WWRS > WWRN. This paper’s optimization framework and research results can effectively guide the design of the ULEB in severely cold regions.

Under carbon peaking and neutrality constraints, low-carbon retrofitting of residential buildings (LRRB) has become a strategic need for most countries worldwide. However, the development of China’s LRRB market still relies on government guidance without moving towards the goal of autonomous orientation. This area is still a concern for academics. Moreover, many stakeholders are involved in the LRRB, and the secondary stakeholders’ behavioral strategies do not substantially impact the LRRB. So, this paper adopts Mitchell’s score-based approach to identify the core stakeholders, followed by a tripartite evolutionary game model of government, ESCOs, and owners. Based on the system dynamics (SD) model, the evolution rules of the three parties’ behavior strategies and evolution stabilization strategies are analyzed, and the key factors influencing the equilibrium are found. The results of the study show that under the condition that the government adopts the same level of subsidy for ESCOs and owners, ESCOs are more sensitive to the subsidy; with the introduction of penalties under the premise of subsidy, ESCOs can reach evolutionary equilibrium faster; and when the benefits of owners accepting LRRB outweigh the losses, owners will eventually choose to accept retrofit regardless of whether the government subsidizes owners or not. Finally, the paper ends with suggestions for developing an LRRB market. The game model proposed in this paper can provide a scientific reference for stakeholders’ carbon reduction decisions.