The pursuit of human-level artificial intelligence (AI) has significantly advanced the development of autonomous agents and Large Language Models (LLMs). LLMs are now widely utilized as decision-making agents for their ability to interpret instructions, manage sequential tasks, and adapt through feedback. This review examines recent developments in employing LLMs as autonomous agents and tool users and comprises seven research questions. We only used the papers published between 2023 and 2025 in conferences of the A* and A rank and Q1 journals. A structured analysis of the LLM agents' architectural design principles, dividing their applications into single-agent and multi-agent systems, and strategies for integrating external tools is presented. In addition, the cognitive mechanisms of LLM, including reasoning, planning, and memory, and the impact of prompting methods and fine-tuning procedures on agent performance are also investigated. Furthermore, we evaluated current benchmarks and assessment protocols and have provided an analysis of 68 publicly available datasets to assess the performance of LLM-based agents in various tasks. In conducting this review, we have identified critical findings on verifiable reasoning of LLMs, the capacity for self-improvement, and the personalization of LLM-based agents. Finally, we have discussed ten future research directions to overcome these gaps.

Knowledge distillation (KD) has traditionally relied on a static teacher-student framework, where a large, well-trained teacher transfers knowledge to a single student model. However, these approaches often suffer from knowledge degradation, inefficient supervision, and reliance on either a very strong teacher model or large labeled datasets. To address these, we present the first-ever Weakly-supervised Chain-based KD network (WeCKD) that redefines knowledge transfer through a structured sequence of interconnected models. Unlike conventional KD, it forms a progressive distillation chain, where each model not only learns from its predecessor but also refines the knowledge before passing it forward. This structured knowledge transfer further enhances feature learning and addresses the limitations of one-step KD. Each model in the chain is trained on only a fraction of the dataset and shows that effective learning can be achieved with minimal supervision. Extensive evaluation on six imaging datasets across otoscopic, microscopic, and magnetic resonance imaging modalities shows that it generalizes and outperforms existing methods. Furthermore, the proposed distillation chain resulted in cumulative accuracy gains of up to +23% over a single backbone trained on the same limited data, which highlights its potential for real-world adoption.

The increasing use of synthetic media, particularly deepfakes, is an emerging challenge for digital content verification. Although recent studies use both audio and visual information, most integrate these cues within a single model, which remains vulnerable to modality mismatches, noise, and manipulation. To address this gap, we propose DeepAgent, an advanced multi-agent collaboration framework that simultaneously incorporates both visual and audio modalities for the effective detection of deepfakes. DeepAgent consists of two complementary agents. Agent-1 examines each video with a streamlined AlexNet-based CNN to identify the symbols of deepfake manipulation, while Agent-2 detects audio-visual inconsistencies by combining acoustic features, audio transcriptions from Whisper, and frame-reading sequences of images through EasyOCR. Their decisions are fused through a Random Forest meta-classifier that improves final performance by taking advantage of the different decision boundaries learned by each agent. This study evaluates the proposed framework using three benchmark datasets to demonstrate both component-level and fused performance. Agent-1 achieves a test accuracy of 94.35% on the combined Celeb-DF and FakeAVCeleb datasets. On the FakeAVCeleb dataset, Agent-2 and the final meta-classifier attain accuracies of 93.69% and 81.56%, respectively. In addition, cross-dataset validation on DeepFakeTIMIT confirms the robustness of the meta-classifier, which achieves a final accuracy of 97.49%, and indicates a strong capability across diverse datasets. These findings confirm that hierarchy-based fusion enhances robustness by mitigating the weaknesses of individual modalities and demonstrate the effectiveness of a multi-agent approach in addressing diverse types of manipulations in deepfakes.

Accurate land cover classification from satellite imagery is crucial in environmental monitoring and sustainable resource management. However, it remains challenging due to the complexity of natural landscapes, the visual similarity between classes, and the significant class imbalance in the available datasets. To address these issues, we propose a dual encoder architecture that independently extracts modality-specific features from optical and Synthetic Aperture Radar (SAR) imagery, which are then fused using a cross-modality attention-fusion module named Cross-modality Land cover segmentation with Attention and Imbalance- aware Reasoning-Enhanced Explanations (CLAIRE). This fusion mechanism highlights complementary spatial and textural features, enabling the network to better capture detailed and diverse land cover patterns. We incorporate a hybrid loss function that utilizes Weighted Focal Loss and Tversky Loss named RIFT (Rare-Instance Focal-Tversky) to address class imbalance and improve segmentation performance across underrepresented categories. Our model achieves competitive performance across multiple benchmarks: a mean Intersection over Union (mIoU) of 56.02% and Overall Accuracy (OA) of 84.56% on the WHU-OPT-SAR dataset; strong generalization with a mIoU of 59.89% and OA of 73.92% on the OpenEarthMap-SAR dataset; and remarkable robustness under cloud-obstructed conditions, achieving an mIoU of 86.86% and OA of 94.58% on the PIE-RGB-SAR dataset. Additionally, we introduce a metric-driven reasoning module generated by a Small Language Model (Phi-3), which generates expert-level, sample-specific justifications for model predictions, thereby enhancing transparency and interpretability.

In the past few years, artificial intelligence (AI) techniques have been implemented in almost all verticals of human life. However, the results generated from the AI models often lag explainability. AI models often appear as a blackbox wherein developers are unable to explain or trace back the reasoning behind a specific decision. Explainable AI (XAI) is a rapid growing field of research which helps to extract information and also visualize the results generated with an optimum transparency. The present study provides and extensive review of the use of XAI in cybersecurity. Cybersecurity enables protection of systems, networks and programs from different types of attacks. The use of XAI has immense potential in predicting such attacks. The paper provides a brief overview on cybersecurity and the various forms of attack. Then the use of traditional AI techniques and its associated challenges are discussed which opens its doors towards use of XAI in various applications. The XAI implementations of various research projects and industry are also presented. Finally, the lessons learnt from these applications are highlighted which act as a guide for future scope of research.

Discovering user preferences across different domains is pivotal in cross-domain recommendation systems, particularly when platforms lack comprehensive user-item interactive data. The limited presence of shared users often hampers the effective modeling of common preferences. While leveraging shared items' attributes, such as category and popularity, can enhance cross-domain recommendation performance, the scarcity of shared items between domains has limited research in this area. To address this, we propose a Coherence-guided Preference Disentanglement (CoPD) method aimed at improving cross-domain recommendation by i) explicitly extracting shared item attributes to guide the learning of shared user preferences and ii) disentangling these preferences to identify specific user interests transferred between domains. CoPD introduces coherence constraints on item embeddings of shared and specific domains, aiding in extracting shared attributes. Moreover, it utilizes these attributes to guide the disentanglement of user preferences into separate embeddings for interest and conformity through a popularity-weighted loss. Experiments conducted on real-world datasets demonstrate the superior performance of our proposed CoPD over existing competitive baselines, highlighting its effectiveness in enhancing cross-domain recommendation performance.

Large language models (LLMs) are increasingly evident for accurate question answering across various domains. However, rigorous evaluation of their performance on complex question-answering (QA) capabilities is essential before deployment in real-world biomedical and healthcare applications. This paper presents our approach to the MedHopQA track of the BioCreative IX shared task, which focuses on multi-hop biomedical question answering involving diseases, genes, and chemicals. We adopt a supervised fine-tuning strategy leveraging LLaMA 3 8B, enhanced with a curated biomedical question-answer dataset compiled from external sources including BioASQ, MedQuAD, and TREC. Three experimental setups are explored: fine-tuning on combined short and long answers, short answers only, and long answers only. While our models demonstrate strong domain understanding, achieving concept-level accuracy scores of up to 0.8, their Exact Match (EM) scores remain significantly lower, particularly in the test phase. We introduce a two-stage inference pipeline for precise short-answer extraction to mitigate verbosity and improve alignment with evaluation metrics. Despite partial improvements, challenges persist in generating strictly formatted outputs. Our findings highlight the gap between semantic understanding and exact answer evaluation in biomedical LLM applications, motivating further research in output control and post-processing strategies.

Automated birdsong classification is essential for advancing ecological monitoring and biodiversity studies. Despite recent progress, existing methods often depend heavily on labeled data, use limited feature representations, and overlook temporal dynamics essential for accurate species identification. In this work, we propose a self-supervised contrastive network, ARIONet (Acoustic Representation for Interframe Objective Network), that jointly optimizes contrastive classification and future frame prediction using augmented audio representations. The model simultaneously integrates multiple complementary audio features within a transformer-based encoder model. Our framework is designed with two key objectives: (1) to learn discriminative species-specific representations for contrastive learning through maximizing similarity between augmented views of the same audio segment while pushing apart different samples, and (2) to model temporal dynamics by predicting future audio frames, both without requiring large-scale annotations. We validate our framework on four diverse birdsong datasets, including the British Birdsong Dataset, Bird Song Dataset, and two extended Xeno-Canto subsets (A-M and N-Z). Our method consistently outperforms existing baselines and achieves classification accuracies of 98.41%, 93.07%, 91.89%, and 91.58%, and F1-scores of 97.84%, 94.10%, 91.29%, and 90.94%, respectively. Furthermore, it demonstrates low mean absolute errors and high cosine similarity, up to 95%, in future frame prediction tasks. Extensive experiments further confirm the effectiveness of our self-supervised learning strategy in capturing complex acoustic patterns and temporal dependencies, as well as its potential for real-world applicability in ecological conservation and monitoring.

People exhibit unique emotional responses. In the same scenario, the emotional reactions of two individuals can be either similar or vastly different. For instance, consider one person's reaction to an invitation to smoke versus another person's response to a query about their sleep quality. The identification of these individual traits through the observation of common physical parameters opens the door to a wide range of applications, including psychological analysis, criminology, disease prediction, addiction control, and more. While there has been previous research in the fields of psychometrics, inertial sensors, computer vision, and audio analysis, this paper introduces a novel technique for identifying human traits in real time using brainwave data. To achieve this, we begin with an extensive study of brainwave data collected from 80 participants using a portable EEG headset. We also conduct a statistical analysis of the collected data utilizing box plots. Our analysis uncovers several new insights, leading us to a groundbreaking unified approach for identifying diverse human traits by leveraging machine learning techniques on EEG data. Our analysis demonstrates that this proposed solution achieves high accuracy. Moreover, we explore two deep-learning models to compare the performance of our solution. Consequently, we have developed an integrated, real-time trait identification solution using EEG data, based on the insights from our analysis. To validate our approach, we conducted a rigorous user evaluation with an additional 20 participants. The outcomes of this evaluation illustrate both high accuracy and favorable user ratings, emphasizing the robust potential of our proposed method to serve as a versatile solution for human trait identification.

We introduce reputable citations (RC), a method to screen and segment a collection of papers by decoupling popularity and influence. We demonstrate RC using recent works published in a large set of mathematics journals from Clarivate's Incites Essential Science Indicators, leveraging Clarivate's Web of Science for citation reports and assigning prestige values to institutions based on well-known international rankings. We compare researchers drawn from two samples: highly cited researchers (HC) and mathematicians whose influence is acknowledged by peers (Control). RC scores distinguish the influence of researchers beyond citations, revealing highly cited mathematical work of modest influence. The control group, comprising peer-acknowledged researchers, dominates the top tier of RC scores despite having fewer total citations than the HC group. Influence, as recognized by peers, does not always correlate with high citation counts, and RC scores offer a nuanced distinction between the two. With development, RC scores could automate screening of citations to identify exceptional and influential research, while addressing manipulative practices. The first application of RC reveals mathematics works that may be cited for reasons unrelated to genuine research advancements, suggesting a need for continued development of this method to mitigate such trends.

Internet of Underwater Things (IoUT) have gained rapid momentum over the past decade with applications spanning from environmental monitoring and exploration, defence applications, etc. The traditional IoUT systems use machine learning (ML) approaches which cater the needs of reliability, efficiency and timeliness. However, an extensive review of the various studies conducted highlight the significance of data privacy and security in IoUT frameworks as a predominant factor in achieving desired outcomes in mission critical applications. Federated learning (FL) is a secured, decentralized framework which is a recent development in machine learning, that will help in fulfilling the challenges faced by conventional ML approaches in IoUT. This paper presents an overview of the various applications of FL in IoUT, its challenges, open issues and indicates direction of future research prospects.

Insect classification is important for agricultural management and ecological research, as it directly affects crop health and production. However, this task remains challenging due to the complex characteristics of insects, class imbalance, and large-scale datasets. To address these issues, we propose BioAutoML-NAS, the first BioAutoML model using multimodal data, including images, and metadata, which applies neural architecture search (NAS) for images to automatically learn the best operations for each connection within each cell. Multiple cells are stacked to form the full network, each extracting detailed image feature representations. A multimodal fusion module combines image embeddings with metadata, allowing the model to use both visual and categorical biological information to classify insects. An alternating bi-level optimization training strategy jointly updates network weights and architecture parameters, while zero operations remove less important connections, producing sparse, efficient, and high-performing architectures. Extensive evaluation on the BIOSCAN-5M dataset demonstrates that BioAutoML-NAS achieves 96.81% accuracy, 97.46% precision, 96.81% recall, and a 97.05% F1 score, outperforming state-of-the-art transfer learning, transformer, AutoML, and NAS methods by approximately 16%, 10%, and 8% respectively. Further validation on the Insects-1M dataset obtains 93.25% accuracy, 93.71% precision, 92.74% recall, and a 93.22% F1 score. These results demonstrate that BioAutoML-NAS provides accurate, confident insect classification that supports modern sustainable farming.

Accurate land cover classification from satellite imagery is crucial in environmental monitoring and sustainable resource management. However, it remains challenging due to the complexity of natural landscapes, the visual similarity between classes, and the significant class imbalance in the available datasets. To address these issues, we propose a dual encoder architecture that independently extracts modality-specific features from optical and Synthetic Aperture Radar (SAR) imagery, which are then fused using a cross-modality attention-fusion module named Cross-modality Land cover segmentation with Attention and Imbalance- aware Reasoning-Enhanced Explanations (CLAIRE). This fusion mechanism highlights complementary spatial and textural features, enabling the network to better capture detailed and diverse land cover patterns. We incorporate a hybrid loss function that utilizes Weighted Focal Loss and Tversky Loss named RIFT (Rare-Instance Focal-Tversky) to address class imbalance and improve segmentation performance across underrepresented categories. Our model achieves competitive performance across multiple benchmarks: a mean Intersection over Union (mIoU) of 56.02% and Overall Accuracy (OA) of 84.56% on the WHU-OPT-SAR dataset; strong generalization with a mIoU of 59.89% and OA of 73.92% on the OpenEarthMap-SAR dataset; and remarkable robustness under cloud-obstructed conditions, achieving an mIoU of 86.86% and OA of 94.58% on the PIE-RGB-SAR dataset. Additionally, we introduce a metric-driven reasoning module generated by a Small Language Model (Phi-3), which generates expert-level, sample-specific justifications for model predictions, thereby enhancing transparency and interpretability.

Accurate liver and tumor segmentation on abdominal CT images is critical for reliable diagnosis and treatment planning, but remains challenging due to complex anatomical structures, variability in tumor appearance, and limited annotated data. To address these issues, we introduce Hyperbolic-convolutions Adaptive-temporal-attention with Neural-representation and Synaptic-plasticity Network (HANS-Net), a novel segmentation framework that synergistically combines hyperbolic convolutions for hierarchical geometric representation, a wavelet-inspired decomposition module for multi-scale texture learning, a biologically motivated synaptic plasticity mechanism for adaptive feature enhancement, and an implicit neural representation branch to model fine-grained and continuous anatomical boundaries. Additionally, we incorporate uncertainty-aware Monte Carlo dropout to quantify prediction confidence and lightweight temporal attention to improve inter-slice consistency without sacrificing efficiency. Extensive evaluations of the LiTS dataset demonstrate that HANS-Net achieves a mean Dice score of 93.26%, an IoU of 88.09%, an average symmetric surface distance (ASSD) of 0.72 mm, and a volume overlap error (VOE) of 11.91%. Furthermore, cross-dataset validation on the 3D-IRCADb-01 dataset obtains an average Dice of 87.45%, IoU of 80.30%, ASSD of 1.525 mm, and VOE of 19.71%, indicating strong generalization across different datasets. These results confirm the effectiveness and robustness of HANS-Net in providing anatomically consistent, accurate, and confident liver and tumor segmentation.

Effective oscillator strength distributions are systematically generated and tabulated for the alkali atoms, the alkaline-earth atoms, the alkaline-earth ions, the rare gases and some miscellaneous atoms. These effective distributions are used to compute the dipole, quadrupole and octupole static polarizabilities, and are then applied to the calculation of the dynamic polarizabilities at imaginary frequencies. These polarizabilities can be used to determine the long-range $C_6$, $C_8$ and $C_{10}$ atom-atom interactions for the dimers formed from any of these atoms and ions, and we present tables covering all of these combinations.

Proximally-sensed laser scanning offers significant potential for automated forest data capture, but challenges remain in automatically identifying tree species without additional ground data. Deep learning (DL) shows promise for automation, yet progress is slowed by the lack of large, diverse, openly available labeled datasets of single tree point clouds. This has impacted the robustness of DL models and the ability to establish best practices for species classification. To overcome these challenges, the FOR-species20K benchmark dataset was created, comprising over 20,000 tree point clouds from 33 species, captured using terrestrial (TLS), mobile (MLS), and drone laser scanning (ULS) across various European forests, with some data from other regions. This dataset enables the benchmarking of DL models for tree species classification, including both point cloud-based (PointNet++, MinkNet, MLP-Mixer, DGCNNs) and multi-view image-based methods (SimpleView, DetailView, YOLOv5). 2D image-based models generally performed better (average OA = 0.77) than 3D point cloud-based models (average OA = 0.72), with consistent results across different scanning platforms and sensors. The top model, DetailView, was particularly robust, handling data imbalances well and generalizing effectively across tree sizes. The FOR-species20K dataset, available at this https URL, is a key resource for developing and benchmarking DL models for tree species classification using laser scanning data, providing a foundation for future advancements in the field.

Internet of Things (IoT) is a disruptive technology with applications across diverse domains such as transportation and logistics systems, smart grids, smart homes, connected vehicles, and smart cities. Alongside the growth of these infrastructures, the volume and variety of attacks on these infrastructures has increased highlighting the significance of distinct protection mechanisms. Intrusion detection is one of the distinguished protection mechanisms with notable recent efforts made to establish effective intrusion detection for IoT and IoV. However, unique characteristics of such infrastructures including battery power, bandwidth and processors overheads, and the network dynamics can influence the operation of an intrusion detection system. This paper presents a comprehensive study of existing intrusion detection systems for IoT systems including emerging systems such as Internet of Vehicles (IoV). The paper analyzes existing systems in three aspects: computational overhead, energy consumption and privacy implications. Based on a rigorous analysis of the existing intrusion detection approaches, the paper also identifies open challenges for an effective and collaborative design of intrusion detection system for resource-constrained IoT system in general and its applications such as IoV. These efforts are envisaged to highlight state of the art with respect to intrusion detection for IoT and open challenges requiring specific efforts to achieve efficient intrusion detection within these systems.

Face recognition is a biometric which is attracting significant research, commercial and government interest, as it provides a discreet, non-intrusive way of detecting, and recognizing individuals, without need for the subject's knowledge or consent. This is due to reduced cost, and evolution in hardware and algorithms which have improved their ability to handle unconstrained conditions. Evidently affordable and efficient applications are required. However, there is much debate over which methods are most appropriate, particularly in the context of the growing importance of deep neural network-based face recognition systems. This systematic review attempts to provide clarity on both issues by organizing the plethora of research and data in this field to clarify current research trends, state-of-the-art methods, and provides an outline of their benefits and shortcomings. Overall, this research covered 1,330 relevant studies, showing an increase of over 200% in research interest in the field of face recognition over the past 6 years. Our results also demonstrated that deep learning methods are the prime focus of modern research due to improvements in hardware databases and increasing understanding of neural networks. In contrast, traditional methods have lost favor amongst researchers due to their inherent limitations in accuracy, and lack of efficiency when handling large amounts of data.

The Universal Morphology (UniMorph) project is a collaborative effort providing broad-coverage instantiated normalized morphological inflection tables for hundreds of diverse world languages. The project comprises two major thrusts: a language-independent feature schema for rich morphological annotation and a type-level resource of annotated data in diverse languages realizing that schema. This paper presents the expansions and improvements made on several fronts over the last couple of years (since McCarthy et al. (2020)). Collaborative efforts by numerous linguists have added 67 new languages, including 30 endangered languages. We have implemented several improvements to the extraction pipeline to tackle some issues, e.g. missing gender and macron information. We have also amended the schema to use a hierarchical structure that is needed for morphological phenomena like multiple-argument agreement and case stacking, while adding some missing morphological features to make the schema more inclusive. In light of the last UniMorph release, we also augmented the database with morpheme segmentation for 16 languages. Lastly, this new release makes a push towards inclusion of derivational morphology in UniMorph by enriching the data and annotation schema with instances representing derivational processes from MorphyNet.