This paper uses the EBM model to measure the collaborative governance efficiency of air pollution caused by energy consumption in 27 cities in the Yangtze River Delta (YRD) urban agglomeration. The collaborative governance efficiency of these cities ranges from 0.6665 to 0.9356, with Shanghai having the highest efficiency (0.8277-0.9356) and Chuzhou having the lowest (0.6665-0.8787). On this basis, this article uses a spatial Durbin model and government panel data to test the drivers of air pollution collaborative governance efficiency, the empirical testing found that the relationship between environmental regulation intensity (ERI) and air collaborative governance efficiency (AGE) is U-shaped, with an inverse coefficient of impact of - 0.5852 and a positive coefficient of influence of its squared term of 0.3427. Air pollution governance investment level (AGI) has a 0.8107 positive effect on governance efficiency. All spatial lag term coefficients in the spatial test are positive, indicating a spatial spillover effect of collaborative governance efficiency air pollution caused by energy consumption across cities in the urban agglomeration. In addition, control variables: energy consumption intensity (ECI), the air quality index (AQI), per capita CO2 emission scale (PCE), and air pollution loss rate (ALI), had inverse correlations with governance efficiency, with impact coefficients of - 0.5185, - 0.5107, - 0.6164, and - 0.5147. Per capita, GDP level (PGL) and R & D investment intensity (RDII) had positive relationships with governance efficiency with coefficients of 0.6026 and 0.5786, respectively. Based on this foundation, policy recommendations have been proposed to enhance the collaborative governance efficiency of air pollution in the Yangtze River Delta urban cluster.