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.

Secure and scalable electronic medical record (EMR) sharing is essential for cross-institutional collaboration, yet existing blockchain-based approaches can incur high on-chain overhead under bursty, fine-grained, and temporary authorization. We propose Secure and Scalable Tokenized EMR Sharing on a Permissioned Blockchain, referred to as SST-MedChain, a patient-centric framework that (i) enables patient-side non-interactive delegation via an Elliptic Curve Diffie–Hellman (ECDH)-derived verification token protected by a hash commitment, and (ii) reduces on-chain authorization to a near constant-time token lookup and atomic state transition using one-time access tokens. SST-MedChain further supports policy-bounded cascading re-delegation and fast revocation over deployment-bounded delegation chains via a Nested Freezing state machine and a Source Circuit Breaker. Experiments on FISCO BCOS (a permissioned blockchain platform) in a wide area network (WAN) show that, on the evaluated on-chain confirmation path, SST-MedChain improves throughput by 38% and reduces latency by 86% compared with Attribute-Based Access Control (ABAC) at 300 queries per second (QPS), and achieves 16.5% higher throughput than MedShare at 1000 QPS with comparatively stable average confirmation latency.