Paper Title
AI for Fake News: A Systematic Survey of Detection and Summarization Techniques, Research Trends, and Future Directions

Abstract
Digital misinformation greatly harms the information ecosystem.. Gradually, the field of AI-enabled fake news detection (fnd) is beginning to flourish. This study focuses on providing an overview of the most recent advancements in AI-enabled fake news detection and summarization. We describe and analyze 30 groundwork papers published between 2017 and 2025 obtained from major academic repositories like IEEE Xplore and arXiv. Our work classifies them according to the main approaches, which are deep learning, transformers (BERT, GPT), or other machine learning techniques. We discuss the trends in the number of publications, main data sets used, and the spread of the studies in various publishing venues, including journals, conferences, and preprints. This paper reports on the technical growth of the field, presents the present state of it, and also notes a key issue in the design of real time, large scale, and cross language validation systems. We provide a structured review for researchers and a clear framework of which we see research going forward. Keywords - Multi Agent Architecture, Fake News Detector, Real Time Validation