Comprehensive Survey on AI-Enhanced Software Systems: From Misinformation Detection to Distributed Infrastructure Optimization

The rapid advancement of artificial intelligence technologies has transformed the landscape of modern software systems, introducing both unprecedented capabilities and novel challenges. This comprehensive survey examines recent innovations in AI-driven systems across multiple critical domains: misinformation detection and prevention in large language models, agricultural applications of machine learning from a software engineering perspective, distributed database optimization using adaptive graph neural networks, automated test case generation with formal quality guarantees, advanced graph database architectures, cloud computing infrastructure optimization, security mechanisms for distributed systems, scalable national compute frameworks, and intelligent customer support systems. Through systematic analysis of these interconnected research areas, we identify common patterns, emerging methodologies, and future research directions. Our survey synthesizes contributions that leverage causal inference, graph neural networks, retrieval-augmented generation, and multi-modal learning frameworks to address fundamental challenges in trustworthiness, scalability, security, and performance optimization. This work provides researchers and practitioners with a holistic understanding of state-of-the-art AI systems and their practical implications for building reliable, efficient, and secure software infrastructure.