Abstract

Abstract
Product design is a complex and iterative process that requires the balance of multiple constraints, such as material selection, manufacturability, regulatory compliance, and structural integrity, among others. Traditional design workflows follow a human-driven approach, limiting efficiency, adaptability, and the ability to quickly respond to evolving limitations. This paper introduces an agentic approach to product design, leveraging multi-agent systems to distribute and automate design tasks dynamically. To demonstrate this methodology, a hypothetical enclosure design is used as a guiding example, demonstrating how agents interact to generate product specifications, select materials, validate structural properties, assess manufacturability, and perform other relevant tasks throughout the design process. To implement this framework, CrewAI is utilized as an agent coordination system that enables the structured definition of roles and execution of tasks for autonomous agents. In the final section, a case study is presented, focusing on the design of a parallelepiped enclosure, applying the proposed framework in a simulated environment. Our findings highlight the advantages of agent-based collaboration in product design, showcasing its potential to optimize workflows, reduce development time, and improve adaptability to changing requirements. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Abstract
Eye diseases, such as glaucoma, diabetic retinopathy, and age-related macular degeneration, drive the growing need for reliable and scalable analyses of fundus and optical coherence tomography (OCT) images. Deep learning performs strongly in ocular structure segmentation. However, it typically relies on dense pixel-wise annotations, which are costly and difficult to obtain at scale. Weakly supervised learning (WSL) can reduce this burden by leveraging coarse labels, limited strong annotations, and unlabeled data. This systematic umbrella review synthesizes survey and review articles on weakly supervised deep learning for image segmentation, with a focus on ocular imaging (fundus and OCT/OCTA). After analyzing twenty-one secondary studies, the main finding reveals an empty intersection: WSL-focused segmentation surveys are often modality-agnostic. Conversely, ocular reviews are predominantly fully supervised and seldom offer quantitative evidence on annotation-effort savings or direct comparisons between weak and fully supervised methods on identical datasets. Across the included reviews, label-efficient strategies cluster around CAM/MIL formulations, sparse supervision (points/scribbles/boxes), pseudo-labelling/self-training, and semi-/self-supervised learning, implemented mainly with U-Net/DeepLab families and increasingly Transformer or hybrid backbones. These results provide a structured map of available WSL mechanisms and, critically, identify reproducible reporting gaps that currently prevent fair benchmarking in ocular segmentation. Therefore, this review supports the development of ocular-specific benchmarks and minimum reporting practices that link segmentation performance to annotation effort.

Abstract
Efficient battery management in electric vehicles plays a key role in the transition to more sustainable and energy efficient mobility. This article presents a proposal for a modular framework to optimise charging and energy consumption based on solar radiation prediction. The solution integrates three main components: climate prediction models, battery behaviour simulation, and optimisation algorithms for decision making. This approach aims to dynamically adapt charging strategies to maximise vehicle autonomy and reduce energy waste. The modularity of the framework allows it to be applied to different vehicle types and operating contexts, ensuring flexibility and scalability. In addition, preliminary studies on solar radiation forecasting have already been carried out, providing a basis for future development of the system. The implementation of this approach represents an important step towards more efficient energy management in electric vehicles, contributing to the reduction of environmental impact and the promotion of sustainable electric mobility. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Abstract
Log analysis is fundamental to modern software observability systems, playing a key role in improving system reliability. Recently, there has been a growing adoption of Large Language Models (LLMs) for log anomaly detection, due to their ability to learn complex patterns. In this work, we propose a model-agnostic framework that allows seamless plug-and-play integration of different LLMs, making it easy to experiment with and select the model that fits specific needs. These models are first fine-tuned on normal log data, learning their patterns. During inference, the model predicts the most probable next tokens based on the preceding context in each sequence. Anomaly detection is performed using Top-K predictions, where sequences are flagged as anomalous if the actual log entry does not appear among the K most probable next tokens, with K determined using the validation dataset. The proposed framework is evaluated on three widely-used benchmark datasets-HDFS, BGL, and Thunderbird-where it consistently achieves competitive results, outperforming state-of-the-art methods in multiple scenarios. These results highlight the effectiveness of LLM-based log analysis and the importance of flexibility when selecting models for specific operational contexts.

Abstract
Fact-checking remains a demanding and time-consuming task, still largely dependent on manual verification and unable to match the rapid spread of misinformation online. This is particularly important because debunking false information typically takes longer to reach consumers than the misinformation itself; accelerating corrections through automation can therefore help counter it more effectively. Although many organizations perform manual fact-checking, this approach is difficult to scale given the growing volume of digital content. These limitations have motivated interest in automating fact-checking, where identifying claims is a crucial first step. However, progress has been uneven across languages, with English dominating due to abundant annotated data. Portuguese, like other languages, still lacks accessible, licensed datasets, limiting research, Natural Language Processing (NLP) developments, and applications. In this paper, we introduce ClaimPT, a dataset of European Portuguese news articles annotated for factual claims, comprising 1,308 articles and 6,875 individual annotations. Unlike most existing resources based on social media or parliamentary transcripts, ClaimPT focuses on journalistic content, collected through a partnership with LUSA, the Portuguese News Agency. To ensure annotation quality, two trained annotators labeled each article, with a curator validating all annotations according to a newly proposed scheme. We also provide baseline models for claim detection, establishing initial benchmarks and enabling future NLP and Information Retrieval (IR) applications. By releasing ClaimPT, we aim to advance research on low-resource fact-checking and enhance understanding of misinformation in news media.