OBJECTIVE: This survey aims to systematically map the rapidly evolving landscape of AI agents in healthcare. It addresses the critical need to adapt general-purpose agentic frameworks characterized by autonomy, planning, and tool use to the high-stakes, safety-critical constraints of medical decision-making and patient care. METHODS: We conducted a comprehensive review of over 200 recent studies, synthesizing literature from major academic databases. We developed a holistic taxonomy that traces the full lifecycle of healthcare agents, analyzing perception modalities, core technical architectures, and evaluation protocols specific to autonomous systems. RESULTS: The review presents a quantitative landscape analysis showing exponential growth in the field. We structure the domain into three pillars: (1) Perception of multi-modal clinical data (e.g., EHR, imaging, genomics); (2) Agent Capabilities, including tool use, reasoning, memory, and multi-agent collaboration; and (3) an Application Ecosystem organized by stakeholder roles (clinicians, patients, researchers, and administrators). Additionally, we categorize evaluation frameworks, and discuss the deployment readiness of current systems across technical, evidentiary, and governance dimensions. Finally, we identify challenges for advancing healthcare agents from controlled evaluation toward real-world clinical integration. A continuously updated repository of related papers is available at https://github.com/AgenticHealthAI/Awesome-AI-Agents-for-Healthcare. CONCLUSION: AI agents offer significant potential to enhance healthcare through autonomous reasoning and workflow integration. However, current research remains largely concentrated in benchmark and controlled evaluation settings, and the translation into clinical practice will require advances in reliability, privacy protection, governance, and operational integration.

Integrated sensing and communication (ISAC), as a rapidly advancing technique, introduces a fresh approach for achieving secure communication and intelligent sensing for future wireless networks. An ISAC framework empowered by simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RIS) is explored in this paper, where a base station equipped with multiple antennas establishes wireless links to users each with a single antenna during the detection of a point target. The point target, regarded as an eavesdropper, trying to intercept users’ information. Cramér-Rao bound (CRB) serves as evaluation criterion to assess sensing accuracy of point eavesdropper, whereas the secrecy rate is employed to quantify the security level of the communication link. To optimize sensing-communication tradeoff, a joint optimization problem is constructed. To approach the formulated problem, a hybrid Block Coordinate Descent (BCD)-based algorithm is developed, which alternately updates the transmission beamforming and STAR-RIS phase shifts, using successive convex approximation (SCA) technique, penalty dual decomposition (PDD) framework and projected gradient method (PGM).

Gene regulatory network (GRN) inference is essential for understanding gene interactions that control biological functions and disease progression. Its goal is to uncover regulatory relationships among genes using gene expression data, such as single-cell RNA sequencing (scRNA-seq). With the rise of deep learning, numerous approaches-particularly those using Graph Neural Networks (GNNs)-have shown promising progress in GRN inference. However, scRNA-seq datasets exhibit high sparsity, noise, dropout events, and cellular heterogeneity. These characteristics make it difficult for fixed GNN architectures to generalize across scRNA-seq datasets, often leading to performance degradation. To address this challenge, we propose AutoGRN, an automated graph neural network framework for gene regulatory network inference tasks. AutoGRN incorporates a range of components that potentially influence GRN inference performance into its search space. Through a genetic search algorithm constrained by information entropy, AutoGRN identifies optimal GNN architectures by adapting to the characteristics of individual datasets. Experimental results show that AutoGRN outperforms existing methods in prediction accuracy across multiple public datasets.

A time-varying formation tracking (TVFT) control method under denial-of-service (DoS) attacks is proposed for a class of multi-uncrewed aerial vehicle (UAV) system with unknown nonlinearity. The neural network approximation is utilized to mitigate the impact of nonlinear dynamics on the tracking performance. Meanwhile, the switching topologies are adopted to ensure the reliability of the communication topology. Considering the resource constraints of the system communication network, an improved integral event-triggered mechanism is devised to further decrease the triggering frequency in comparison to the traditional event-triggered one. By using the multi-Lyapunov function, the tracking error is proved to be bounded. Simulations convincingly demonstrate the effectiveness and merits of the developed TVFT and the integral event-triggered method. Note to Practitioners—Multi-UAV systems are widely utilized in both civil and military domains, with communication networks serving as crucial channels for information exchange among UAVs. However, these communication networks are often vulnerable to various types of attacks. Therefore, the control problems of multi-UAV systems under DoS attacks are of great importance. A switching event-triggered control protocol is developed for multi-UAV systems to facilitate effective formation tracking in the presence of DoS attacks. This protocol employs switching topologies to enhance the reliability and flexibility of the communication network. The improved event-triggered mechanism effectively balances the system performance and the communication consumption.

Replicating data over a cluster of workstations is a powerful tool to increase performance, and provide fault-tolerance for demanding database applications. The big challenge in such systems is to combine replica control (keeping the copies consistent) with concurrency control. Most of the research so far has focused on providing the traditional correctness criteria serializability. However, more and more database systems, e.g., Oracle and PostgreSQL, use multi-version concurrency control providing the isolation level snapshot isolation. In this paper, we present Postgres-R(SI), an extension of PostgreSQL offering transparent replication. Our replication tool is designed to work smoothly with PostgreSQL's concurrency control providing snapshot isolation for the entire replicated system. We present a detailed description of the replica control algorithm, and how it is combined with PostgreSQL's concurrency control component. Furthermore, we discuss some challenges we encountered when implementing the protocol. Our performance analysis based on the TPC-W benchmark shows that this approach exhibits excellent performance for real-life applications even if they are update intensive.