The issue of data-driven neural network model construction is one of the core problems in the domain of Artificial Intelligence. A standard approach assumes a fixed architecture with trainable weights. A conceptually more advanced assumption is that we not only train the weights, but also find out the optimal model architecture. We present a new method that realizes just that. This article is an extended version of our conference paper titled "Dynamic Growing and Shrinking of Neural Networks with Monte Carlo Tree Search [26]". In the paper, we show in detail how to create a neural network with a procedure that allows dynamic shrinking and growing of the model while it is being trained. The decision-making mechanism for the architectural design is governed by a Monte Carlo tree search procedure which simulates network behavior and allows to compare several candidate architecture changes to choose the best one. The proposed method was validated using both visual and time series datasets, demonstrating its particular effectiveness in multivariate time series classification. This is attributed to the architecture's ability to adapt dynamically, allowing independent modifications for each time series. The approach is supplemented by Python source code for reproducibility. Experimental evaluations in visual pattern and multivariate time series classification tasks revealed highly promising performance, underscoring the method's robustness and adaptability.

In 2021, Google set a lofty goal of achieving net-zero carbon emissions by 2030. Yet in the years since then, the company has moved in the opposite direction as it invests in energy-intensive artificial intelligence. In its latest sustainability report, Google said its carbon emissions had increased 51% between 2019 and 2024. New research aims to debunk even that enormous figure and provide context to Google's sustainability reports, painting a bleaker picture. A report authored by non-profit advocacy group Kairos Fellowship found that, between 2019 and 2024, Google's carbon emissions actually went up by 65%.

A Ukrainian drone attack on an industrial plant in Izhevsk, in central Russia, killed three people and injured 35 others, regional Governor Alexander Brechalov said in a post on Telegram. The drone struck the Kupol Electromechanical Plant, which produces air defence systems and drones for the Russian military, an unnamed official with Ukraine's Security Service, the SBU, told the Associated Press news agency. A Russian attack on a vehicle evacuating civilians from Pokrovsk, in Ukraine's Donetsk region, killed one person and injured a policeman, police said. The Ministry of Defence in Moscow said that 60 Ukrainian drones were downed overnight over several regions, including 17 over Russian-occupied Crimea, 16 over Russia's Rostov region and four over Russia's Saratov region. Ukraine's Air Force said on Tuesday that Russia launched 52 Shahed and decoy drones at the country overnight.

In this paper, we present a novel framework for enhancing model interpretability by integrating heatmaps produced separately by ResNet and a restructured 2D Transformer with globally weighted input saliency. We address the critical problem of spatial-temporal misalignment in existing interpretability methods, where convolutional networks fail to capture global context and Transformers lack localized precision - a limitation that impedes actionable insights in safety-critical domains like healthcare and industrial monitoring. Our method merges gradient-weighted activation maps (ResNet) and Transformer attention rollout into a unified visualization, achieving full spatial-temporal alignment while preserving real-time performance. Empirical evaluations on clinical (ECG arrhythmia detection) and industrial (energy consumption prediction) datasets demonstrate significant improvements: the hybrid framework achieves 94.1% accuracy (F1 0.93) on the PhysioNet dataset and reduces regression error to RMSE = 0.28 kWh (R2 = 0.95) on the UCI Energy Appliance dataset-outperforming standalone ResNet, Transformer, and InceptionTime baselines by 3.8-12.4%. An NLP module translates fused heatmaps into domain-specific narratives (e.g., "Elevated ST-segment between 2-4 seconds suggests myocardial ischemia"), validated via BLEU-4 (0.586) and ROUGE-L (0.650) scores. By formalizing interpretability as causal fidelity and spatial-temporal alignment, our approach bridges the gap between technical outputs and stakeholder understanding, offering a scalable solution for transparent, time-aware decision-making.

In recent years, \emph{Reinforcement Learning} (RL) has made remarkable progress, achieving superhuman performance in a wide range of simulated environments. As research moves toward deploying RL in real-world applications, the field faces a new set of challenges inherent to real-world settings, such as large state-action spaces, non-stationarity, and partial observability. Despite their importance, these challenges are often underexplored in current benchmarks, which tend to focus on idealized, fully observable, and stationary environments, often neglecting to incorporate real-world complexities explicitly. In this paper, we introduce \texttt{Gym4ReaL}, a comprehensive suite of realistic environments designed to support the development and evaluation of RL algorithms that can operate in real-world scenarios. The suite includes a diverse set of tasks that expose algorithms to a variety of practical challenges. Our experimental results show that, in these settings, standard RL algorithms confirm their competitiveness against rule-based benchmarks, motivating the development of new methods to fully exploit the potential of RL to tackle the complexities of real-world tasks.

Large language models (LLMs) have enabled powerful advances in natural language understanding and generation. Yet their application to complex, real-world scientific workflows remain limited by challenges in memory, planning, and tool integration. Here, we introduce SciBORG (Scientific Bespoke Artificial Intelligence Agents Optimized for Research Goals), a modular agentic framework that allows LLM-based agents to autonomously plan, reason, and achieve robust and reliable domain-specific task execution. Agents are constructed dynamically from source code documentation and augmented with finite-state automata (FSA) memory, enabling persistent state tracking and context-aware decision-making. This approach eliminates the need for manual prompt engineering and allows for robust, scalable deployment across diverse applications via maintaining context across extended workflows and to recover from tool or execution failures. We validate SciBORG through integration with both physical and virtual hardware, such as microwave synthesizers for executing user-specified reactions, with context-aware decision making and demonstrate its use in autonomous multi-step bioassay retrieval from the PubChem database utilizing multi-step planning, reasoning, agent-to-agent communication and coordination for execution of exploratory tasks. Systematic benchmarking shows that SciBORG agents achieve reliable execution, adaptive planning, and interpretable state transitions. Our results show that memory and state awareness are critical enablers of agentic planning and reliability, offering a generalizable foundation for deploying AI agents in complex environments.

With the rise of large language models, the paradigm of training foundation models with massive parameter counts on vast datasets has been adopted in multiple domains to achieve remarkable success. Time series foundation models represent a significant extension of this paradigm, demonstrating exceptional expressive power, generalization, and cross-domain transferability. However, this gives rise to a fundamental paradox: time series data reflect distinct dynamical systems, making cross-domain transfer intuitively implausible, yet this is contradicted by the models' empirical success. To resolve this paradox, this paper investigates, from both theoretical and experimental perspectives, the representation learning mechanisms and generalization capabilities of patch-based time series foundation models. We argue that such models are not merely applying a new architecture but are fundamentally generalizing the representation paradigm of language models by extending deterministic vector-based representations to latent probabilistic distributional forms. Our theoretical analysis supports this framework by demonstrating that continuous time-series patches can be faithfully quantized into a discrete vocabulary whose key statistical properties are highly consistent with those of natural language. This generalization allows time series models to inherit the robust representation and transfer abilities of large language models, thereby explaining their superior performance in temporal tasks. Ultimately, our work provides a rigorous theoretical cornerstone for understanding, evaluating, and improving the safety and reliability of large-scale time series foundation models.

Human reliability remains a critical concern in safety-critical domains such as nuclear power, where operational failures are often linked to human error. While conventional human reliability analysis (HRA) methods have been widely adopted, they rely heavily on expert judgment for identifying human failure events (HFEs) and assigning performance influencing factors (PIFs). This reliance introduces challenges related to reproducibility, subjectivity, and limited integration of interface-level data. In particular, current approaches lack the capacity to rigorously assess how human-machine interface design contributes to operator performance variability and error susceptibility. To address these limitations, this study proposes a framework for risk-informed human failure event identification and interface-induced risk assessment driven by AutoGraph (InSight-R). By linking empirical behavioral data to the interface-embedded knowledge graph (IE-KG) constructed by the automated graph-based execution framework (Auto-Graph), the InSight-R framework enables automated HFE identification based on both error-prone and time-deviated operational paths. Furthermore, we discuss the relationship between designer-user conflicts and human error. This framework offers actionable insights for interface design optimization and contributes to the advancement of mechanism-driven HRA methodologies. Keywords: Knowledge-Graph-Driven, Automated, Interface-Induced Risk, Human Error Identification 1 Introduction Human error remains a leading contributor to failures in complex socio-technical systems such as nuclear power plants, aviation, and healthcare, where safety-critical operations depend on accurate and timely human decisions [1, 2]. Human reliability analysis (HRA) methods have been widely used to model operator behavior and assess the likelihood of human failure events (HFEs) [3]. However, prevailing HRA approaches are often constrained by their reliance on expert judgment, particularly in the identification of HFEs and the assignment of performance influencing factors (PIFs) [3, 4]. In traditional HRA frameworks such as the integrated human event analysis system for event and condition assessment (IDHEAS-ECA), HFEs are primarily determined through expert elicitation, a process that, while practical, suffers from limited reproducibility, insufficient transparency, and weak theoretical grounding [5].

--Accurate electrochemical models are essential for the safe and efficient operation of lithium-ion batteries in real-world applications such as electrified vehicles and grid storage. Reduced-order models (ROM) offer a balance between fidelity and computational efficiency but often struggle to capture complex and nonlinear behaviors, such as the dynamics in the cell voltage response under high C-rate conditions. T o address these limitations, this study proposes an Adaptive Ensemble Sparse Identification (AESI) framework that enhances the accuracy of reduced-order li-ion battery models by compensating for unpredictable dynamics. The approach integrates an Extended Single Particle Model (ESPM) with an evolutionary ensemble sparse learning strategy to construct a robust hybrid model. In addition, the AESI framework incorporates a conformal prediction method to provide theoretically guaranteed uncertainty quantification for voltage error dynamics, thereby improving the reliability of the model's predictions. Evaluation across diverse operating conditions shows that the hybrid model (ESPM + AESI) improves the voltage prediction accuracy, achieving mean squared error reductions of up to 46% on unseen data. Prediction reliability is further supported by conformal prediction, yielding statistically valid prediction intervals with coverage ratios of 96.85% and 97.41% for the ensemble models based on bagging and stability selection, respectively.

The long-standing vision of intelligent cities is to create efficient, livable, and sustainable urban environments using big data and artificial intelligence technologies. Recently, the advent of Large Language Models (LLMs) has opened new ways toward realizing this vision. With powerful semantic understanding and reasoning capabilities, LLMs can be deployed as intelligent agents capable of autonomously solving complex problems across domains. In this article, we focus on Urban LLM Agents, which are LLM-powered agents that are semi-embodied within the hybrid cyber-physical-social space of cities and used for system-level urban decision-making. First, we introduce the concept of urban LLM agents, discussing their unique capabilities and features. Second, we survey the current research landscape from the perspective of agent workflows, encompassing urban sensing, memory management, reasoning, execution, and learning. Third, we categorize the application domains of urban LLM agents into five groups: urban planning, transportation, environment, public safety, and urban society, presenting representative works in each group. Finally, we discuss trustworthiness and evaluation issues that are critical for real-world deployment, and identify several open problems for future research. This survey aims to establish a foundation for the emerging field of urban LLM agents and to provide a roadmap for advancing the intersection of LLMs and urban intelligence. A curated list of relevant papers and open-source resources is maintained and continuously updated at https://github.com/usail-hkust/Awesome-Urban-LLM-Agents.