The combination of LLM agents with external tools enables models to solve complex tasks beyond their knowledge base. Human-designed tools are inflexible and restricted to solutions within the scope of pre-existing tools created by experts. To address this problem, we propose ATLASS, an advanced tool learning and selection system designed as a closed-loop framework. It enables the LLM to solve problems by dynamically generating external tools on demand. In this framework, agents play a crucial role in orchestrating tool selection, execution, and refinement, ensuring adaptive problem-solving capabilities. The operation of ATLASS follows three phases: The first phase, Understanding Tool Requirements, involves the Agents determining whether tools are required and specifying their functionality; the second phase, Tool Retrieval/Generation, involves the Agents retrieving or generating tools based on their availability; and the third phase, Task Solving, involves combining all the component tools necessary to complete the initial task. The Tool Dataset stores the generated tools, ensuring reusability and minimizing inference cost. Current LLM-based tool generation systems have difficulty creating complex tools that need APIs or external packages. In ATLASS, we solve the problem by automatically setting up the environment, fetching relevant API documentation online, and using a Python interpreter to create a reliable, versatile tool that works in a wider range of situations. OpenAI GPT-4.0 is used as the LLM agent, and safety and ethical concerns are handled through human feedback before executing generated code. By addressing the limitations of predefined toolsets and enhancing adaptability, ATLASS serves as a real-world solution that empowers users with dynamically generated tools for complex problem-solving.

The deployment of artificial intelligence models at the edge is increasingly critical for autonomous robots operating in GPS-denied environments where local, resource-efficient reasoning is essential. This work demonstrates the feasibility of deploying small Vision-Language Models (VLMs) on mobile robots to achieve real-time scene understanding and reasoning under strict computational constraints. Unlike prior approaches that separate perception from mobility, the proposed framework enables simultaneous movement and reasoning in dynamic environments using only on-board hardware. The system integrates a compact VLM with multimodal perception to perform contextual interpretation directly on embedded hardware, eliminating reliance on cloud connectivity. Experimental validation highlights the balance between computational efficiency, task accuracy, and system responsiveness. Implementation on a mobile robot confirms one of the first successful deployments of small VLMs for concurrent reasoning and mobility at the edge. This work establishes a foundation for scalable, assured autonomy in applications such as service robotics, disaster response, and defense operations.

Current state of the art measures like BLEU, CIDEr, VQA score, SigLIP-2 and CLIPScore are often unable to capture semantic or structural accuracy, especially for domain-specific or context-dependent scenarios. For this, this paper proposes a Physics-Constrained Multimodal Data Evaluation (PCMDE) metric combining large language models with reasoning, knowledge based mapping and vision-language models to overcome these limitations. The architecture is comprised of three main stages: (1) feature extraction of spatial and semantic information with multimodal features through object detection and VLMs; (2) Confidence-Weighted Component Fusion for adaptive component-level validation; and (3) physics-guided reasoning using large language models for structural and relational constraints (e.g., alignment, position, consistency) enforcement.

The IceCube Neutrino Observatory is a cubic-kilometer-scale high-energy neutrino detector built into the ice at the South Pole. Construction of IceCube, the largest neutrino detector built to date, was completed in 2011 and enabled the discovery of high-energy astrophysical neutrinos. We describe here the design, production, and calibration of the IceCube digital optical module (DOM), the cable systems, computing hardware, and our methodology for drilling and deployment. We also describe the online triggering and data filtering systems that select candidate neutrino and cosmic ray events for analysis. Due to a rigorous pre-deployment protocol, 98.4% of the DOMs in the deep ice are operating and collecting data. IceCube routinely achieves a detector uptime of 99% by emphasizing software stability and monitoring. Detector operations have been stable since construction was completed, and the detector is expected to operate at least until the end of the next decade.

Immediate damage assessment is essential after natural catastrophes; yet, conventional hand evaluation techniques are sluggish and perilous. Although satellite and unmanned aerial vehicle (UAV) photos offer extensive perspectives of impacted regions, current computer vision methodologies generally yield just classification labels or segmentation masks, so constraining their capacity to deliver a thorough situational comprehension. We introduce the Vision Language Caption Enhancer (VLCE), a multimodal system designed to produce comprehensive, contextually-informed explanations of disaster imagery. VLCE employs a dual-architecture approach: a CNN-LSTM model with a ResNet50 backbone pretrained on EuroSat satellite imagery for the xBD dataset, and a Vision Transformer (ViT) model pretrained on UAV pictures for the RescueNet dataset. Both systems utilize external semantic knowledge from ConceptNet and WordNet to expand vocabulary coverage and improve description accuracy. We assess VLCE in comparison to leading vision-language models (LLaVA and QwenVL) utilizing CLIPScore for semantic alignment and InfoMetIC for caption informativeness. Experimental findings indicate that VLCE markedly surpasses baseline models, attaining a maximum of 95.33% on InfoMetIC while preserving competitive semantic alignment. Our dual-architecture system demonstrates significant potential for improving disaster damage assessment by automating the production of actionable, information-dense descriptions from satellite and drone photos.

The IceCube neutrino telescope at the South Pole has measured the atmospheric muon neutrino spectrum as a function of zenith angle and energy in the approximate 320 GeV to 20 TeV range, to search for the oscillation signatures of light sterile neutrinos. No evidence for anomalous $\nu_\mu$ or $\bar{\nu}_\mu$ disappearance is observed in either of two independently developed analyses, each using one year of atmospheric neutrino data. New exclusion limits are placed on the parameter space of the 3+1 model, in which muon antineutrinos would experience a strong MSW-resonant oscillation. The exclusion limits extend to $\mathrm{sin}^2 2\theta_{24} \leq$ 0.02 at $\Delta m^2 \sim$0.3$\mathrm{eV}^2$ at the 90\% confidence level. The allowed region from global analysis of appearance experiments, including LSND and MiniBooNE, is excluded at approximately the 99\% confidence level for the global best fit value of $|$U$_{e4}|^2$.

This Letter presents the result of a 3+1 sterile neutrino search using 10.7 years of IceCube data. We analyze atmospheric muon neutrinos that traverse the Earth with energies ranging from 0.5 to 100 TeV, incorporating significant improvements in modeling neutrino flux and detector response compared to earlier studies. Notably, for the first time, we categorize data into starting and through-going events, distinguishing neutrino interactions with vertices inside or outside the instrumented volume, to improve energy resolution. The best-fit point for a 3+1 model is found to be at $\sin^2(2\theta_{24}) = 0.16$ and $\Delta m^{2}_{41} = 3.5$ eV$^2$, which agrees with previous iterations of this study. The result is consistent with the null hypothesis of no sterile neutrinos with a p-value of 3.1\%.

Reduced environmental effect, lower operating costs, and a stable and sustainable energy supply for current and future generations are the main reasons why power optimization is important. Power optimization makes ensuring that energy is used more effectively, cutting down on waste and optimizing the utilization of resources.In today's world, power optimization and artificial intelligence (AI) integration are essential to changing the way energy is produced, used, and distributed. Real-time monitoring and analysis of power usage trends is made possible by AI-driven algorithms and predictive analytics, which enable dynamic modifications to effectively satisfy demand. Efficiency and sustainability are increased when power consumption is optimized in different sectors thanks to the use of intelligent systems. This survey paper comprises an extensive review of the several AI techniques used for power optimization as well as a methodical analysis of the literature for the study of various intelligent system application domains across different disciplines of power consumption.This literature review identifies the performance and outcomes of 17 different research methods by assessing them, and it aims to distill valuable insights into their strengths and limitations. Furthermore, this article outlines future directions in the integration of AI for power consumption optimization.

We analyzed the 7.92$\times 10^{11}$ cosmic-ray-induced muon events collected by the IceCube Neutrino Observatory from May 13, 2011, when the fully constructed experiment started to take data, to May 12, 2023. This dataset provides an up-to-date cosmic-ray arrival direction distribution in the Southern Hemisphere with unprecedented statistical accuracy covering more than a full period length of a solar cycle. Improvements in Monte Carlo event simulation and better handling of year-to-year differences in data processing significantly reduce systematic uncertainties below the level of statistical fluctuations compared to the previously published results. We confirm the observation of a change in the angular structure of the cosmic-ray anisotropy between 10 TeV and 1 PeV, more specifically in the 100-300 TeV energy range.

Cities today generate enormous streams of data from sensors, cameras, and connected infrastructure. While this information offers unprecedented opportunities to improve urban life, most existing systems struggle with scale, latency, and fragmented insights. This work introduces a framework that blends physics-informed machine learning, multimodal data fusion, and knowledge graph representation with adaptive, rule-based intelligence powered by large language models (LLMs). Physics-informed methods ground learning in real-world constraints, ensuring predictions remain meaningful and consistent with physical dynamics. Knowledge graphs act as the semantic backbone, integrating heterogeneous sensor data into a connected, queryable structure. At the edge, LLMs generate context-aware rules that adapt filtering and decision-making in real time, enabling efficient operation even under constrained resources. Together, these elements form a foundation for digital twin systems that go beyond passive monitoring to provide actionable insights. By uniting physics-based reasoning, semantic data fusion, and adaptive rule generation, this approach opens new possibilities for creating responsive, trustworthy, and sustainable smart infrastructures.

Traditional clustering techniques often rely solely on similarity in the input data, limiting their ability to capture structural or semantic constraints that are critical in many domains. We introduce the Domain Aware Rule Triggered Variational Autoencoder (DARTVAE), a rule guided multimodal clustering framework that incorporates domain specific constraints directly into the representation learning process. DARTVAE extends the VAE architecture by embedding explicit rules, semantic representations, and data driven features into a unified latent space, while enforcing constraint compliance through rule consistency and violation penalties in the loss function. Unlike conventional clustering methods that rely only on visual similarity or apply rules as post hoc filters, DARTVAE treats rules as first class learning signals. The rules are generated by LLMs, structured into knowledge graphs, and enforced through a loss function combining reconstruction, KL divergence, consistency, and violation penalties. Experiments on aircraft and automotive datasets demonstrate that rule guided clustering produces more operationally meaningful and interpretable clusters for example, isolating UAVs, unifying stealth aircraft, or separating SUVs from sedans while improving traditional clustering metrics. However, the framework faces challenges: LLM generated rules may hallucinate or conflict, excessive rules risk overfitting, and scaling to complex domains increases computational and consistency difficulties. By combining rule encodings with learned representations, DARTVAE achieves more meaningful and consistent clustering outcomes than purely data driven models, highlighting the utility of constraint guided multimodal clustering for complex, knowledge intensive settings.

Energy management decreases energy expenditures and consumption while simultaneously increasing energy efficiency, reducing carbon emissions, and enhancing operational performance. Smart grids are a type of sophisticated energy infrastructure that increase the generation and distribution of electricity's sustainability, dependability, and efficiency by utilizing digital communication technologies. They combine a number of cutting-edge techniques and technology to improve energy resource management. A large amount of research study on the topic of smart grids for energy management has been completed in the last several years. The authors of the present study want to cover a number of topics, including smart grid benefits and components, technical developments, integrating renewable energy sources, using artificial intelligence and data analytics, cybersecurity, and privacy. Smart Grids for Energy Management are an innovative field of study aiming at tackling various difficulties and magnifying the efficiency, dependability, and sustainability of energy systems, including: 1) Renewable sources of power like solar and wind are intermittent and unpredictable 2) Defending smart grid system from various cyber-attacks 3) Incorporating an increasing number of electric vehicles into the system of power grid without overwhelming it. Additionally, it is proposed to use AI and data analytics for better performance on the grid, reliability, and energy management. It also looks into how AI and data analytics can be used to optimize grid performance, enhance reliability, and improve energy management. The authors will explore these significant challenges and ongoing research. Lastly, significant issues in this field are noted, and recommendations for further work are provided.

Muons produced in atmospheric cosmic ray showers account for the by far dominant part of the event yield in large-volume underground particle detectors. The IceCube detector, with an instrumented volume of about a cubic kilometer, has the potential to conduct unique investigations on atmospheric muons by exploiting the large collection area and the possibility to track particles over a long distance. Through detailed reconstruction of energy deposition along the tracks, the characteristics of muon bundles can be quantified, and individual particles of exceptionally high energy identified. The data can then be used to constrain the cosmic ray primary flux and the contribution to atmospheric lepton fluxes from prompt decays of short-lived hadrons. In this paper, techniques for the extraction of physical measurements from atmospheric muon events are described and first results are presented. The multiplicity spectrum of TeV muons in cosmic ray air showers for primaries in the energy range from the knee to the ankle is derived and found to be consistent with recent results from surface detectors. The single muon energy spectrum is determined up to PeV energies and shows a clear indication for the emergence of a distinct spectral component from prompt decays of short-lived hadrons. The magnitude of the prompt flux, which should include a substantial contribution from light vector meson di-muon decays, is consistent with current theoretical predictions.

Gamma-ray bursts (GRBs) have long been considered a possible source of high-energy neutrinos. While no correlations have yet been detected between high-energy neutrinos and GRBs, the recent observation of GRB 221009A - the brightest GRB observed by Fermi-GBM to date and the first one to be observed above an energy of 10 TeV - provides a unique opportunity to test for hadronic emission. In this paper, we leverage the wide energy range of the IceCube Neutrino Observatory to search for neutrinos from GRB 221009A. We find no significant deviation from background expectation across event samples ranging from MeV to PeV energies, placing stringent upper limits on the neutrino emission from this source.

Wounds, such as foot ulcers, pressure ulcers, leg ulcers, and infected wounds, come up with substantial problems for healthcare professionals. Prompt and accurate segmentation is crucial for effective treatment. However, contemporary methods need an exhaustive model that is qualified for both classification and segmentation, especially lightweight ones. In this work, we tackle this issue by presenting a new architecture that incorporates U-Net, which is optimized for both wound classification and effective segmentation. We curated four extensive and diverse collections of wound images, utilizing the publicly available Medetec Dataset, and supplemented with additional data sourced from the Internet. Our model performed exceptionally well, with an F1 score of 0.929, a Dice score of 0.931 in segmentation, and an accuracy of 0.915 in classification, proving its effectiveness in both classification and segmentation work. This accomplishment highlights the potential of our approach to automating wound care management.

A measurement of the diffuse astrophysical neutrino spectrum is presented using IceCube data collected from 2011-2022 (10.3 years). We developed novel detection techniques to search for events with a contained vertex and exiting track induced by muon neutrinos undergoing a charged-current interaction. Searching for these starting track events allows us to not only more effectively reject atmospheric muons but also atmospheric neutrino backgrounds in the southern sky, opening a new window to the sub-100 TeV astrophysical neutrino sky. The event selection is constructed using a dynamic starting track veto and machine learning algorithms. We use this data to measure the astrophysical diffuse flux as a single power law flux (SPL) with a best-fit spectral index of $\gamma = 2.58 ^{+0.10}_{-0.09}$ and per-flavor normalization of $\phi^{\mathrm{Astro}}_{\mathrm{per-flavor}} = 1.68 ^{+0.19}_{-0.22} \times 10^{-18} \times \mathrm{GeV}^{-1} \mathrm{cm}^{-2} \mathrm{s}^{-1} \mathrm{sr}^{-1}$ (at 100 TeV). The sensitive energy range for this dataset is 3 - 550 TeV under the SPL assumption. This data was also used to measure the flux under a broken power law, however we did not find any evidence of a low energy cutoff.

Continued improvements on existing reconstruction methods are vital to the success of high-energy physics experiments, such as the IceCube Neutrino Observatory. In IceCube, further challenges arise as the detector is situated at the geographic South Pole where computational resources are limited. However, to perform real-time analyses and to issue alerts to telescopes around the world, powerful and fast reconstruction methods are desired. Deep neural networks can be extremely powerful, and their usage is computationally inexpensive once the networks are trained. These characteristics make a deep learning-based approach an excellent candidate for the application in IceCube. A reconstruction method based on convolutional architectures and hexagonally shaped kernels is presented. The presented method is robust towards systematic uncertainties in the simulation and has been tested on experimental data. In comparison to standard reconstruction methods in IceCube, it can improve upon the reconstruction accuracy, while reducing the time necessary to run the reconstruction by two to three orders of magnitude.

The IceCube Collaboration has observed a high-energy astrophysical neutrino flux and recently found evidence for neutrino emission from the blazar TXS 0506+056. These results open a new window into the high-energy universe. However, the source or sources of most of the observed flux of astrophysical neutrinos remains uncertain. Here, a search for steady point-like neutrino sources is performed using an unbinned likelihood analysis. The method searches for a spatial accumulation of muon-neutrino events using the very high-statistics sample of about $497\,000$ neutrinos recorded by IceCube between 2009 and 2017. The median angular resolution is $\sim1^\circ$ at 1 TeV and improves to $\sim0.3^\circ$ for neutrinos with an energy of 1 PeV. Compared to previous analyses, this search is optimized for point-like neutrino emission with the same flux-characteristics as the observed astrophysical muon-neutrino flux and introduces an improved event-reconstruction and parametrization of the background. The result is an improvement in sensitivity to the muon-neutrino flux compared to the previous analysis of $\sim35\%$ assuming an $E^{-2}$ spectrum. The sensitivity on the muon-neutrino flux is at a level of $E^2 \mathrm{d} N /\mathrm{d} E = 3\cdot 10^{-13}\,\mathrm{TeV}\,\mathrm{cm}^{-2}\,\mathrm{s}^{-1}$. No new evidence for neutrino sources is found in a full sky scan and in an a priori candidate source list that is motivated by gamma-ray observations. Furthermore, no significant excesses above background are found from populations of sub-threshold sources. The implications of the non-observation for potential source classes are discussed.