Edge Artificial Intelligence (Edge AI) embeds intelligence directly into devices at the network edge, enabling real-time processing with improved privacy and reduced latency by processing data close to its source. This review systematically examines the evolution, current landscape, and future directions of Edge AI through a multi-dimensional taxonomy including deployment location, processing capabilities such as TinyML and federated learning, application domains, and hardware types. Following PRISMA guidelines, the analysis traces the field from early content delivery networks and fog computing to modern on-device intelligence. Core enabling technologies such as specialized hardware accelerators, optimized software, and communication protocols are explored. Challenges including resource limitations, security, model management, power consumption, and connectivity are critically assessed. Emerging opportunities in neuromorphic hardware, continual learning algorithms, edge-cloud collaboration, and trustworthiness integration are highlighted, providing a comprehensive framework for researchers and practitioners.

As distributed artificial intelligence (AI) and multi-agent architectures grow increasingly complex, the need for adaptive, context-aware routing becomes paramount. This paper introduces an enhanced, adaptive routing algorithm tailored for AI multi-agent networks, integrating priority-based cost functions and dynamic learning mechanisms. Building on an extended Dijkstra-based framework, we incorporate multi-faceted parameters such as task complexity, user request priority, agent capabilities, bandwidth, latency, load, model sophistication, and reliability. We further propose dynamically adaptive weighting factors, tuned via reinforcement learning (RL), to continuously evolve routing policies based on observed network performance. Additionally, heuristic filtering and hierarchical routing structures improve scalability and responsiveness. Our approach yields context-sensitive, load-aware, and priority-focused routing decisions that not only reduce latency for critical tasks but also optimize overall resource utilization, ultimately enhancing the robustness, flexibility, and efficiency of multi-agent systems.

Advanced artificial intelligence models can already churn out computer code and help discover new pharmaceuticals, but when it comes to identifying simple objects, they might still have something to learn from the humble rat. Those are the conclusions drawn from a paper published this week in the journal Patterns, where researchers from Scuola Internazionale Superiore di Studi Avanzati (SISSA) in Italy tasked an image recognition model with trying to replicate rats' ability to recognize objects that were rotated, resized, and partially obscured. . The AI model was able to eventually match the rats' image processing capabilities, but only after using more and more resources and computer power to catch up. Though identifying objects in their original position was easy for both the AI and the rat, researchers had to boost the model's performance in order to match the rats processing capabilities when identifying objects that were altered in various ways. Researchers say their findings suggest that rat vision, fine-tuned over millions of years of evolution, is still more efficient than even powerful image recognition systems. Rat vision differs from the way humans see in several notable ways.

Driven by the vision of ubiquitous connectivity and wireless intelligence, the evolution of ultra-dense constellation-based satellite-integrated Internet is underway, now taking preliminary shape. Nevertheless, the entrenched institutional silos and limited, nonrenewable heterogeneous network resources leave current satellite systems struggling to accommodate the escalating demands of next-generation intelligent applications. In this context, the distributed satellite information networks (DSIN), exemplified by the cohesive clustered satellites system, have emerged as an innovative architecture, bridging information gaps across diverse satellite systems, such as communication, navigation, and remote sensing, and establishing a unified, open information network paradigm to support resilient space information services. This survey first provides a profound discussion about innovative network architectures of DSIN, encompassing distributed regenerative satellite network architecture, distributed satellite computing network architecture, and reconfigurable satellite formation flying, to enable flexible and scalable communication, computing and control. The DSIN faces challenges from network heterogeneity, unpredictable channel dynamics, sparse resources, and decentralized collaboration frameworks. To address these issues, a series of enabling technologies is identified, including channel modeling and estimation, cloud-native distributed MIMO cooperation, grant-free massive access, network routing, and the proper combination of all these diversity techniques. Furthermore, to heighten the overall resource efficiency, the cross-layer optimization techniques are further developed to meet upper-layer deterministic, adaptive and secure information services requirements. In addition, emerging research directions and new opportunities are highlighted on the way to achieving the DSIN vision.

Serving disaggregated large language models (LLMs) over tens of thousands of xPU devices (GPUs or NPUs) with reliable performance faces multiple challenges. 1) Ignoring the diversity (various prefixes and tidal requests), treating all the prompts in a mixed pool is inadequate. To facilitate the similarity per scenario and minimize the inner mismatch on P/D (prefill and decoding) processing, fine-grained organization is required, dynamically adjusting P/D ratios for better performance. 2) Due to inaccurate estimation on workload (queue status or maintained connections), the global scheduler easily incurs unnecessary timeouts in prefill. 3) Block-fixed device-to-device (D2D) KVCache transfer over cluster-level RDMA (remote direct memory access) fails to achieve desired D2D utilization as expected. To overcome previous problems, this paper proposes an end-to-end system P/D-Serve, complying with the paradigm of MLOps (machine learning operations), which models end-to-end (E2E) P/D performance and enables: 1) fine-grained P/D organization, mapping the service with RoCE (RDMA over converged ethernet) as needed, to facilitate similar processing and dynamic adjustments on P/D ratios; 2) on-demand forwarding upon rejections for idle prefill, decoupling the scheduler from regular inaccurate reports and local queues, to avoid timeouts in prefill; and 3) efficient KVCache transfer via optimized D2D access. P/D-Serve is implemented upon Ascend and MindSpore, has been deployed over tens of thousands of NPUs for more than eight months in commercial use, and further achieves 60\%, 42\% and 46\% improvements on E2E throughput, time-to-first-token (TTFT) SLO (service level objective) and D2D transfer time. As the E2E system with optimizations, P/D-Serve achieves 6.7x increase on throughput, compared with aggregated LLMs.

The echo state property (ESP) represents a fundamental concept in the reservoir computing (RC) framework that ensures output-only training of reservoir networks by being agnostic to the initial states and far past inputs. However, the traditional definition of ESP does not describe possible non-stationary systems in which statistical properties evolve. To address this issue, we introduce two new categories of ESP: $\textit{non-stationary ESP}$, designed for potentially non-stationary systems, and $\textit{subspace/subset ESP}$, designed for systems whose subsystems have ESP. Following the definitions, we numerically demonstrate the correspondence between non-stationary ESP in the quantum reservoir computer (QRC) framework with typical Hamiltonian dynamics and input encoding methods using non-linear autoregressive moving-average (NARMA) tasks. We also confirm the correspondence by computing linear/non-linear memory capacities that quantify input-dependent components within reservoir states. Our study presents a new understanding of the practical design of QRC and other possibly non-stationary RC systems in which non-stationary systems and subsystems are exploited.

Various mobile applications that comprise dependent tasks are gaining widespread popularity and are increasingly complex. These applications often have low-latency requirements, resulting in a significant surge in demand for computing resources. With the emergence of mobile edge computing (MEC), it becomes the most significant issue to offload the application tasks onto small-scale devices deployed at the edge of the mobile network for obtaining a high-quality user experience. However, since the environment of MEC is dynamic, most existing works focusing on task graph offloading, which rely heavily on expert knowledge or accurate analytical models, fail to fully adapt to such environmental changes, resulting in the reduction of user experience. This paper investigates the task graph offloading in MEC, considering the time-varying computation capabilities of edge computing devices. To adapt to environmental changes, we model the task graph scheduling for computation offloading as a Markov Decision Process (MDP). Then, we design a deep reinforcement learning algorithm (SATA-DRL) to learn the task scheduling strategy from the interaction with the environment, to improve user experience. Extensive simulations validate that SATA-DRL is superior to existing strategies in terms of reducing average makespan and deadline violation.

Autonomous vehicles require more than simple artificial intelligence. A self-driving car receives data from various sources such as sonars, cameras, radars, GPS, and lidars allowing it to navigate in any environment. Information from these devices should be processed quickly, and data volumes are massive. The information from sensors is processed not only by the car's computer in real-time. Some data is sent to peripheral data centers for further analysis.

One exciting avenue in the world of AI research and development is finding ways to shrink AI algorithms to run on smaller devices closer to sensors, motors and people. Developing embedded AI applications that run machine learning on microcontrollers comes with different constraints around power, performance, connectivity and tools. Embedded AI already has various uses: identifying types of physical activity with smartphone sensors, responding to wake words in consumer electronics, monitoring industrial equipment and distinguishing family members from strangers in home security cameras. A range of new tools, such as TinyML and TensorFlow Lite, can simplify the development of smaller, more power-efficient AI algorithms. "The rise of TinyML deployed on microcontrollers enables intelligence to be distributed into more connected products in the physical world, whether they be smart home gadgets, toys, industrial sensors or otherwise," said Jason Shepherd, vice president of ecosystem at edge-computing platform Zededa.

AI technology is associated with making machines and related processes intelligent through the use of advanced computer programming solutions. The AI technology market is poised to grow at a robust pace driven by its increasing adoption in an expanding range of applications in varied industries. The growing need to analyze and interpret burgeoning volumes of data and the escalating demand for advanced AI solutions to improve customer services are expected to fuel growth in the AI market. With significant improvements being seen in data storage capacity, computing power and parallel processing capabilities, the adoption of AI technology in various end-use sectors is on the rise. The rising adoption of cloud-based services and applications, rapid growth of big data, and the increasing need for intelligent virtual assistants are also contributing to the rapid growth of AI market.