Glass powder, a non-degradable waste material, offers significant potential to reduce cement consumption and carbon emissions in concrete production. However, existing mix design methods for glass powder concrete (GPC) fail to systematically balance economic efficiency, environmental sustainability, and mechanical performance. To address this gap, this study proposes an AI-assisted framework integrating machine learning (ML) and Multi-Objective Optimization (MOO) to achieve a sustainable GPC design. A robust database of 1154 experimental records was developed, focusing on five key predictors: cement content, water-to-binder ratio, aggregate composition, glass powder content, and curing age. Seven ML models were optimized via Bayesian tuning, with the Ensemble Tree model achieving superior accuracy (R² = 0.959 on test data). SHapley Additive exPlanations (SHAP) analysis further elucidated the contribution mechanisms and underlying interactions of material components on GPC compressive strength. Subsequently, a MOO framework minimized unit cost and CO₂ emissions while meeting compressive strength targets (15–70 MPa), solved using the NSGA-II algorithm for Pareto solutions and TOPSIS for decision-making. The Pareto-optimal solutions provide actionable guidelines for engineers to align GPC design with circular economy principles and low-carbon policies. This work advances sustainable construction practices by bridging AI-driven innovation with building materials, directly supporting global goals for waste valorization and carbon neutrality.

The construction industry is a high-energy-consumption industry. Nearly 40% of global carbon emissions derive from the construction industry. Prefabricated assembly technology is an effective means of carbon emission reduction, but the incremental cost of prefabricated components is much more expensive than that of cast-in-place components. It is not conducive for enterprises to choose prefabricated assembly technology to decrease emissions. Most of the current studies focus on the carbon-reduction effect of prefabricated assembled buildings, and there are fewer studies related to the impact of cost factors on enterprises’ participation in building carbon reduction. The cost factor will affect the choice of prefabricated assembly technology to reduce carbon emissions. Therefore, it is necessary to analyze the relationship between carbon emissions and costs in prefabricated buildings. Aiming at this problem, this paper proposes a dual-objective method to optimize cost and carbon emissions by using the improved optimization algorithm to solve the problem. Through the analysis of actual cases, the results show that when the prefabrication rate is 35–40%, enterprises can obtain a better carbon-emission-reduction effect by appropriately increasing the cost. When the prefabrication rate is higher than 40%, the carbon-reduction effect that can be obtained by greatly increasing the cost is limited. Therefore, when enterprises decide a prefabrication range of 35–40%, they are able to obtain the maximum carbon-reduction effect with the minimum cost. This study can provide a reference for the government to formulate relevant policies with energy conservation and emission reductions in prefabricated buildings and also can provide a reference for enterprises to make decisions between carbon emission reduction and cost.