Abstract: Artificial intelligence (AI) technologies are becoming vital tools in promoting the resource utilization of industrial solid waste (ISW) and the intelligent development of waste-derived adsorbents. As the preparation of ISW-based adsorbents is increasingly regarded as a promising utilization pathway, it still faces major obstacles such as the complexity and variability of raw materials, the lack of rule-based guidance in process design, and a heavy reliance on trial-and-error parameter optimization. In this context, AI demonstrates significant potential in key stages of adsorbent development, including experimental data extraction and structuring, synthesis pathway design using algorithmic optimization, property-performance relationship modeling through machine learning, and high-throughput virtual screening enabled by intelligent surrogate models. This review summarizes the progress of AI applications in representative porous materials such as metal-organic frameworks, zeolites and biochar, with emphasis on how different AI models, such as artificial neural networks, decision trees and support vector machines, have been employed to guide synthesis conditions, predict adsorption capacity and identify key descriptors. In addition, practical explorations of AI-enabled ISW-derived adsorbent development are reviewed. Finally, key challenges such as fragmented data, limited model interpretability and complex pollutant-material interactions, are discussed. Future research is suggested to focus on building standardized and shareable data infrastructures, incorporating multiscale simulations that couple quantum-level and process-level insights, enhancing model interpretability via explainable AI techniques and fostering interdisciplinary collaboration to advance the intelligent development of ISW-based adsorbents.