Municipal solid waste landfills, which are complex engineering systems, are influenced by coupled mechanical, hydraulic, biochemical, and thermal processes that occur in the waste mass. Current landfill modeling, to understand these intricacies, often relies on complex physical models which is rather time consuming, or simplified numerical or empirical approaches, which can lack generalization or fail to account for all relevant processes. The advancement of artificial intelligence (AI), machine learning (ML), and deep learning (DL) technologies is providing new opportunities to comprehend intricate data sets. These methods have shown promise in various environmental fields, employing data-driven ML/DL models and AI based optimization techniques to simulate complex processes and predict performance. The potential for the use of the same in predicting landfill performance indicators, like gas generation and settlement, is immense. Hence, the aim of the current study is to perform a comprehensive literature review outlining past research efforts integrating AI/ML/DL techniques in predicting landfill gas generation and settlement. Overall, the use of these technologies in landfill modeling is relatively scarce with numerous studies focusing solely on predicting landfill gas generation rates and/or landfill gas compositions. Few studies have also utilized ML-based models to predict settlement based on field-observed data. However, comprehensive usage of the same in predicting other important parameters like long-term temperatures and stabilization periods were not explored. Recently, complex coupled models have been developed to accurately model landfills; however, these models are computationally intense. Hence, integrating AI based models to surrogate such complex numerical models will be very useful to optimize landfill design and operations.