Anomalies are common in network system monitoring. When manifested as network threats to be mitigated, service outages to be prevented, and security risks to be ameliorated, detecting such anomalous network behaviors becomes of great importance. However, the growing scale and complexity of the mobile communication networks, as well as the ever-increasing amount and dimensionality of the network surveillance data, make it extremely difficult to monitor a mobile network and discover abnormal network behaviors. Recent advances in machine learning allow for obtaining near-optimal solutions to complicated decision-making problems with many sources of uncertainty that cannot be accurately characterized by traditional mathematical models. However, most machine learning algorithms are centralized, which renders them inapplicable to a large-scale distributed wireless networks with tens of millions of mobile devices. In this article, we present fog intelligence, a distributed machine learning architecture that enables intelligent wireless network management. It preserves the advantage of both edge processing and centralized cloud computing. In addition, the proposed architecture is scalable, privacy-preserving, and well suited for intelligent management of a distributed wireless network.
Collaborative agentic AI is projected to transform entire industries by enabling AI-powered agents to autonomously perceive, plan, and act within digital environments. Yet, current solutions in this field are all built in isolation, and we are rapidly heading toward a landscape of fragmented, incompatible ecosystems. In this position paper, we argue that interoperability, achieved by the adoption of minimal standards, is essential to ensure open, secure, web-scale, and widely-adopted agentic ecosystems. To this end, we devise a minimal architectural foundation for collaborative agentic AI, named Web of Agents, which is composed of four components: agent-to-agent messaging, interaction interoperability, state management, and agent discovery. Web of Agents adopts existing standards and reuses existing infrastructure where possible. With Web of Agents, we take the first but critical step toward interoperable agentic systems and offer a pragmatic path forward before ecosystem fragmentation becomes the norm.
The increasing adoption of large language models (LLMs) with extended context windows necessitates efficient Key-Value Cache (KVC) management to optimize inference performance. Inference workloads like Retrieval-Augmented Generation (RAG) and agents exhibit high cache reusability, making efficient caching critical to reducing redundancy and improving speed. We analyze real-world KVC access patterns using publicly available traces and evaluate commercial key-value stores like Redis and state-of-the-art RDMA-based systems (CHIME [1] and Sherman [2]) for KVC metadata management. Our work demonstrates the lack of tailored storage solution for KVC prefilling, underscores the need for an efficient distributed caching system with optimized metadata management for LLM workloads, and provides insights into designing improved KVC management systems for scalable, low-latency inference.
Nuclear waste management requires rigorous regulatory compliance assessment, demanding advanced decision-support systems capable of addressing complex legal, environmental, and safety considerations. This paper presents a multi-agent Retrieval-Augmented Generation (RAG) system that integrates large language models (LLMs) with document retrieval mechanisms to enhance decision accuracy through structured agent collaboration. Through a structured 10-round discussion model, agents collaborate to assess regulatory compliance and safety requirements while maintaining document-grounded responses. Implemented on consumer-grade hardware, the system leverages Llama 3.2 and mxbai-embed-large-v1 embeddings for efficient retrieval and semantic representation. A case study of a proposed temporary nuclear waste storage site near Winslow, Arizona, demonstrates the framework's effectiveness. Results show the Regulatory Agent achieves consistently higher relevance scores in maintaining alignment with legal frameworks, while the Safety Agent effectively manages complex risk assessments requiring multifaceted analysis. The system demonstrates progressive improvement in agreement rates between agents across discussion rounds while semantic drift decreases, indicating enhanced decision-making consistency and response coherence. The system ensures regulatory decisions remain factually grounded, dynamically adapting to evolving regulatory frameworks through real-time document retrieval. By balancing automated assessment with human oversight, this framework offers a scalable and transparent approach to regulatory governance. These findings underscore the potential of AI-driven, multi-agent systems in advancing evidence-based, accountable, and adaptive decision-making for high-stakes environmental management scenarios.
In the domain of sponsored search advertising, the focus of Keyphrase recommendation has largely been on exact match types, which pose issues such as high management expenses, limited targeting scope, and evolving search query patterns. Alternatives like Broad match types can alleviate certain drawbacks of exact matches but present challenges like poor targeting accuracy and minimal supervisory signals owing to limited advertiser usage. This research defines the criteria for an ideal broad match, emphasizing on both efficiency and effectiveness, ensuring that a significant portion of matched queries are relevant. We propose BroadGen, an innovative framework that recommends efficient and effective broad match keyphrases by utilizing historical search query data. Additionally, we demonstrate that BroadGen, through token correspondence modeling, maintains better query stability over time. BroadGen's capabilities allow it to serve daily, millions of sellers at eBay with over 2.3 billion items.
With the advancement of energy Internet and energy system integration, the increasing adoption of distributed photovoltaic (PV) systems presents new challenges on smart monitoring and measurement for utility companies, particularly in separating PV generation from net electricity load. Existing methods struggle with feature extraction from net load and capturing the relevance between weather factors. This paper proposes a PV disaggregation method that integrates Hierarchical Interpolation (HI) and multi-head self-attention mechanisms. By using HI to extract net load features and multi-head self-attention to capture the complex dependencies between weather factors, the method achieves precise PV generation predictions. Simulation experiments demonstrate the effectiveness of the proposed method in real-world data, supporting improved monitoring and management of distributed energy systems.
The development of large language models (LLMs) has provided new tools for research in supply chain management (SCM). In this paper, we introduce a retrieval-augmented generation (RAG) framework that dynamically integrates external knowledge into the inference process, and develop a domain-specialized SCM LLM, which demonstrates expert-level competence by passing standardized SCM examinations and beer game tests. We further employ the use of LLMs to conduct horizontal and vertical supply chain games, in order to analyze competition and cooperation within supply chains. Our experiments show that RAG significantly improves performance on SCM tasks. Moreover, game-theoretic analysis reveals that the LLM can reproduce insights from the classical SCM literature, while also uncovering novel behaviors and offering fresh perspectives on phenomena such as the bullwhip effect. This paper opens the door for exploring cooperation and competition for complex supply chain network through the lens of LLMs.
Recalibration of binary probabilistic classifiers to a target prior probability is an important task in areas like credit risk management. We analyse methods for recalibration from a distribution shift perspective. Distribution shift assumptions linked to the area under the curve (AUC) of a probabilistic classifier are found to be useful for the design of meaningful recalibration methods. Two new methods called parametric covariate shift with posterior drift (CSPD) and ROC-based quasi moment matching (QMM) are proposed and tested together with some other methods in an example setting. The outcomes of the test suggest that the QMM methods discussed in the paper can provide appropriately conservative results in evaluations with concave functionals like for instance risk weights functions for credit risk.
Enterprise search systems often struggle to retrieve accurate, domain-specific information due to semantic mismatches and overlapping terminologies. These issues can degrade the performance of downstream applications such as knowledge management, customer support, and retrieval-augmented generation agents. To address this challenge, we propose a scalable hard-negative mining framework tailored specifically for domain-specific enterprise data. Our approach dynamically selects semantically challenging but contextually irrelevant documents to enhance deployed re-ranking models. Our method integrates diverse embedding models, performs dimensionality reduction, and uniquely selects hard negatives, ensuring computational efficiency and semantic precision. Evaluation on our proprietary enterprise corpus (cloud services domain) demonstrates substantial improvements of 15\% in MRR@3 and 19\% in MRR@10 compared to state-of-the-art baselines and other negative sampling techniques. Further validation on public domain-specific datasets (FiQA, Climate Fever, TechQA) confirms our method's generalizability and readiness for real-world applications.
Multi-view multi-object tracking (MVMOT) has found widespread applications in intelligent transportation, surveillance systems, and urban management. However, existing studies rarely address genuinely free-viewpoint MVMOT systems, which could significantly enhance the flexibility and scalability of cooperative tracking systems. To bridge this gap, we first construct the Multi-Drone Multi-Object Tracking (MDMOT) dataset, captured by mobile drone swarms across diverse real-world scenarios, initially establishing the first benchmark for multi-object tracking in arbitrary multi-view environment. Building upon this foundation, we propose \textbf{FusionTrack}, an end-to-end framework that reasonably integrates tracking and re-identification to leverage multi-view information for robust trajectory association. Extensive experiments on our MDMOT and other benchmark datasets demonstrate that FusionTrack achieves state-of-the-art performance in both single-view and multi-view tracking.
The intensification of European agriculture, characterized by increasing farm sizes, landscape simplification and reliance on synthetic pesticides, remains a key driver of biodiversity decline. While many studies have investigated this phenomenon, they often focus on isolated elements, resulting in a lack of holistic understanding and leaving policymakers and farmers with unclear priorities. This study addresses this gap by developing a spatially explicit ecological economic model designed to dissect the complex interplay between landscape structure and pesticide application, and their combined effects on natural enemy populations and farmers' economic returns. In particular, the model investigates how these relationships are modulated by farm size (a crucial aspect frequently overlooked in prior research). By calibrating on the European agricultural sector, we explore the ecological and economic consequences of various policy scenarios. We show that the effectiveness of ecological restoration strategies is strongly contingent upon farm size. Small to medium-sized farms can experience economic benefits from reduced pesticide use when coupled with hedgerow restoration, owing to enhanced natural pest control. In contrast, large farms encounter challenges in achieving comparable economic gains due to inherent landscape characteristics. This highlights the need to account for farm size in agri-environmental policies in order to promote biodiversity conservation and agricultural sustainability.
Growing penetration of distributed generation such as solar PV can increase the risk of over-voltage in distribution grids, affecting network security. Therefore, assessment of the so-called, PV hosting capacity (HC) - the maximum amount of PV that a given grid can accommodate becomes an important practical problem. In this paper, we propose a novel chance-constrained HC estimation framework using Gaussian Process and Logit learning that can account for uncertainty and risk management. Also, we consider the assessment of HC under different voltage control strategies. Our results have demonstrated that the proposed models can achieve high accuracy levels of up to 93% in predicting nodal over-voltage events on IEEE 33-bus and 123-bus test-cases. Thus, these models can be effectively employed to estimate the chance-constrained HC with various risk levels. Moreover, our proposed methods have simple forms and low computational costs of only a few seconds.
In the pursuit of energy net zero within smart cities, transportation electrification plays a pivotal role. The adoption of Electric Vehicles (EVs) keeps increasing, making energy management of EV charging stations critically important. While previous studies have managed to reduce energy cost of EV charging while maintaining grid stability, they often overlook the robustness of EV charging management against uncertainties of various forms, such as varying charging behaviors and possible faults in faults in some chargers. To address the gap, a novel Multi-Agent Reinforcement Learning (MARL) approach is proposed treating each charger to be an agent and coordinate all the agents in the EV charging station with solar photovoltaics in a more realistic scenario, where system faults may occur. A Long Short-Term Memory (LSTM) network is incorporated in the MARL algorithm to extract temporal features from time-series. Additionally, a dense reward mechanism is designed for training the agents in the MARL algorithm to improve EV charging experience. Through validation on a real-world dataset, we show that our approach is robust against system uncertainties and faults and also effective in minimizing EV charging costs and maximizing charging service satisfaction.
Artificial intelligence advances have recently influenced wireless communications, including beam management in fifth-generation (5G) new radio systems. AI-driven models and algorithms are being applied to enhance tasks such as beam selection, prediction, and refinement by leveraging real-time and historical data. These approaches address challenges such as mobility under complex channel conditions, showing promising results compared to traditional methods. Beam management in 5G refers to processes that ensure optimal alignment between the base station and user equipment for effective signal transmission and reception based on real-time channel state information and user positioning. This study leverages accurate beam prediction to identify a smaller subset of beams, resulting in a more efficient, streamlined, and link-adaptive communication system. The innovative approach presented introduces a precise, attention-based prediction model that derives the entire downlink transmission chain in a commercial grade 5G system. The predicted downlink beams are specifically tailored to handle the complexities of none line-of-sight environments known for high-dimensional channel dynamics and scatterer-induced signal variations. This novel method introduces a paradigm shift in utilizing environmental and channel dynamics in contrast to conventional procedures of beam management, which entails complex methods involving exhaustive techniques to predict the best beams. The presented beam prediction results demonstrate robustness in addressing the challenges posed by signal-dispersive environments, showcasing great potential in mobility scenarios.
Relational databases are central to modern data management, yet most data exists in unstructured forms like text documents. To bridge this gap, we leverage large language models (LLMs) to automatically synthesize a relational database by generating its schema and populating its tables from raw text. We introduce SQUiD, a novel neurosymbolic framework that decomposes this task into four stages, each with specialized techniques. Our experiments show that SQUiD consistently outperforms baselines across diverse datasets.
Linked Data and labelled property graphs (LPG) are two data management approaches with complementary strengths and weaknesses, making their integration beneficial for sharing datasets and supporting software ecosystems. In this paper, we introduce rdf2pg, an extensible framework for mapping RDF data to semantically equivalent LPG formats and data-bases. Utilising this framework, we perform a comparative analysis of three popular graph databases - Virtuoso, Neo4j, and ArcadeDB - and the well-known graph query languages SPARQL, Cypher, and Gremlin. Our qualitative and quantitative as-sessments underline the strengths and limitations of these graph database technologies. Additionally, we highlight the potential of rdf2pg as a versatile tool for enabling polyglot access to knowledge graphs, aligning with established standards of Linked Data and the Semantic Web.
Traditional Identity and Access Management (IAM) systems, primarily designed for human users or static machine identities via protocols such as OAuth, OpenID Connect (OIDC), and SAML, prove fundamentally inadequate for the dynamic, interdependent, and often ephemeral nature of AI agents operating at scale within Multi Agent Systems (MAS), a computational system composed of multiple interacting intelligent agents that work collectively. This paper posits the imperative for a novel Agentic AI IAM framework: We deconstruct the limitations of existing protocols when applied to MAS, illustrating with concrete examples why their coarse-grained controls, single-entity focus, and lack of context-awareness falter. We then propose a comprehensive framework built upon rich, verifiable Agent Identities (IDs), leveraging Decentralized Identifiers (DIDs) and Verifiable Credentials (VCs), that encapsulate an agents capabilities, provenance, behavioral scope, and security posture. Our framework includes an Agent Naming Service (ANS) for secure and capability-aware discovery, dynamic fine-grained access control mechanisms, and critically, a unified global session management and policy enforcement layer for real-time control and consistent revocation across heterogeneous agent communication protocols. We also explore how Zero-Knowledge Proofs (ZKPs) enable privacy-preserving attribute disclosure and verifiable policy compliance. We outline the architecture, operational lifecycle, innovative contributions, and security considerations of this new IAM paradigm, aiming to establish the foundational trust, accountability, and security necessary for the burgeoning field of agentic AI and the complex ecosystems they will inhabit.
In this research a real time power hardware in loop configuration has been implemented for an microgrid with the combination of distribution energy resources such as photovoltaic, grid tied inverter, battery, utility grid, and a diesel generator. This paper introduces an unique adaptive multi-objective optimization approach that employs weighted optimization techniques for real-time microgrid systems. The aim is to effectively balance various factors including fuel consumption, load mismatch, power quality, battery degradation, and the utilization of renewable energy sources. A real time experimental data from power hardware in loop system has been used for dynamically updating system states. The adaptive preference-based selection method are adjusted based on state of battery charging thresholds. The technique has been integrated with six technical objectives and complex constraints. This approach helps to practical microgrid decision making and optimization of dynamic energy systems. The energy management process were also able to maximize photovoltaic production where minimizing power mismatch, stabilizing battery state of charge under different condition. The research results were also compared with the baseline system without optimization techniques, and a reliable outcome was found.
Large language models (LLMs) offer unprecedented and growing capabilities, but also introduce complex safety and security challenges that resist conventional risk management. While conventional probabilistic risk analysis (PRA) requires exhaustive risk enumeration and quantification, the novelty and complexity of these systems make PRA impractical, particularly against adaptive adversaries. Previous research found that risk management in various fields of engineering such as nuclear or civil engineering is often solved by generic (i.e. field-agnostic) strategies such as event tree analysis or robust designs. Here we show how emerging risks in LLM-powered systems could be met with 100+ of these non-probabilistic strategies to risk management, including risks from adaptive adversaries. The strategies are divided into five categories and are mapped to LLM security (and AI safety more broadly). We also present an LLM-powered workflow for applying these strategies and other workflows suitable for solution architects. Overall, these strategies could contribute (despite some limitations) to security, safety and other dimensions of responsible AI.
Waste management is a critical global issue with significant environmental and public health implications. It has become more destructive during large-scale events such as the annual pilgrimage to Makkah, Saudi Arabia, one of the world's largest religious gatherings. This event's popularity has attracted millions worldwide, leading to significant and un-predictable accumulation of waste. Such a tremendous number of visitors leads to in-creased waste management issues at the Grand Mosque and other holy sites, highlighting the need for an effective solution other than traditional methods based on rigid collection schedules. To address this challenge, this research proposed an innovative solution that is context-specific and tailored to the unique requirements of pilgrimage season: a Smart Waste Management System, called TUHR, that utilizes the Internet of Things and Artificial Intelligence. This system encompasses ultrasonic sensors that monitor waste levels in each container at the performance sites. Once the container reaches full capacity, the sensor communicates with the microcontroller, which alerts the relevant authorities. Moreover, our system can detect harmful substances such as gas from the gas detector sensor. Such a proactive and dynamic approach promises to mitigate the environmental and health risks associated with waste accumulation and enhance the cleanliness of these sites. It also delivers economic benefits by reducing unnecessary gasoline consumption and optimizing waste management resources. Importantly, this research aligns with the principles of smart cities and exemplifies the innovative, sustainable, and health-conscious approach that Saudi Arabia is implementing as part of its Vision 2030 initiative.