Over $3.1 trillion in illicit money moves through the global financial system yearly, and much of it now uses stablecoins, which launderers prefer for their liquidity. Decentralized protocols increasingly hide transaction patterns with zero-knowledge proofs, while centralized stablecoins remain visible. To preserve the ability to convert to fiat, they must maintain an auditable record, which makes them natural points of compliance oversight. Using this visibility, we create an Ethereum dataset of Tether USD (USDT) and USD Coin (USDC) wallet transfers and establish a baseline for behavioral anti-money-laundering (AML) detection. We compare linear models, tree ensembles, deep networks,  and graph neural networks. Tree ensembles achieve the best Macro-F1 score, while the graph neural networks lose accuracy as the transaction network fragments. The models separate distinct typologies rather than only flagging suspicion: the fast, dispersed movement of cybercrime wallets is distinguished from the constrained, static footprint of sanctioned or frozen wallets. These results align with the industry shift toward deterministic verification and address the auditability and compliance requirements now forming under regulations such as the EU’s Markets in Crypto-Assets (MiCA) and the U.S. Guiding and Establishing National Innovation for U.S. Stablecoins Act (GENIUS Act), while limiting unjustified  asset freezes. A high-precision behavioral classification of suspicious wallets raises the economic cost of financial misconduct and informs compliance practice under emerging stablecoin rules.

Blockchain transaction data exhibit heterogeneous structures, complex interactions, and highly imbalanced distributions, which pose significant challenges for unsupervised anomaly detection. Existing methods often fail to effectively model the intrinsic feature distributions of normal transactions and typically lack interpretability, limiting their reliability and usability in practical blockchain scenarios. To address these issues, this paper proposes an unsupervised anomaly detection framework based on feature distribution learning. The core idea is to explicitly model the distribution of normal transaction behavior in a compact latent space while preserving interpretability. Specifically, a Kolmogorov–Arnold Network (KAN) is employed to learn a two-dimensional latent representation of blockchain transactions, capturing nonlinear relationships between features. During training, the model minimizes the radius of  a hypersphere enclosing normal samples, encouraging a compact and structured distribution. During inference, anomalies are identified based on their geometric deviation from the learned distribution, measured by the distance to the latent-space center. This design avoids reliance on reconstruction errors  and enables a more direct and stable decision mechanism. Experiments on Ethereum, Blockchain Network Attack Traffic dataset (BNaT) and Real World Dataset of Cryptocurrency Addresses with Transaction Profiles (Real-CATS) demonstrate that the proposed method consistently outperforms state-of-the-art unsupervised baselines across multiple metrics. Furthermore, the symbolic expressions derived from the learned mapping reveal key transaction features that drive anomaly detection decisions, providing clear interpretability. These results highlight the effectiveness, robustness, and practical value of feature distribution learning for blockchain anomaly detection.

With the increase of artificial intelligence (AI) agents being used in the operation of digital systems, they can perform complex tasks, manage resources and interact with distributed environments. However, they require additional support in checking the execution, assigning duties and guaranteeing reliability. Therefore, it is difficult to achieve autonomous decision-making along with stable system operation. Consequently, blockchain is regarded not only as a platform for decentralized applications but also as a dependable base for AI agents. Hence, the present blockchain architectures should not only enhance their efficiency but also ensure traceable state modifications, authentic operations and coordinated communications among various AI-related activities. Therefore, our paper investigates the transaction processing and expanding methods from different perspectives. We classify the previous research into five parts: state control and security measures, improvement of sharding, scalability of consensus and Layer-2 architectures, parallel transaction processing systems and application-oriented trading procedures. For each part, we introduce some typical systems, describe their features in design and evaluate the influences on constructing scalable and trustworthy AI agent systems. Besides, we point out the difficulties in establishing the blockchain framework for AI agents. Finally, this survey presents the existing technologies systematically and highlights their importance.