Text-to-SQL systems have transitioned from simple machine translation models to complex reasoning frameworks as database schemas grow in scale and ambiguity. Despite the impressive capabilities of Large Language Models, one-shot generation often fails to produce correct SQL in real-world scenarios. This survey introduces the Agentic-SQL Taxonomy, an autonomy-based classification [21] that reevaluates existing methods through the lens of inference complexity. We categorize research into single-turn generation, iterative refinement, and multi-agent collaboration to highlight the shift toward interactive debugging and collective reasoning. We analyze how these sophisticated pipelines bridge the performance gap on challenging benchmarks. Current evaluations show that leading models can result in incorrect execution in nearly 40 % of cases when instructions are vague or incomplete. Our work identifies executionguided feedback and modular agent architectures as the primary drivers of future progress in building robust and reliable database interfaces.

The decentralized structure of cryptocurrency has changed modern finance, but its anonymity also allows for many illegal acts such as money laundering, phishing, and other frauds. This paper presents a hybrid detection system. It combines Convolutional Neural Networks (CNN) and Graph Neural Networks (GNN) to find suspicious Ethereum transactions. We use data from May 2022, June 2022, and July 2024. CNNs pull out local transaction details. GNNs map how accounts connect. The node features are then classified with ensemble tools like Random Forest and XGBoost. This brings clear gains over older models-up to 5.79% higher precision and 18.1% higher recall. Tests on July 2024 data spotted new fraud types, including NFT scams and WazirX hack-linked transfers. This shows the model works well for protecting DeFi systems. CCS CONCEPTS Mathematics of computing ~Probability and statistics ~Probabilistic inference problems