Ensuring safety is a foundational requirement for large language models (LLMs). Achieving an appropriate balance between enhancing the utility of model outputs and mitigating their potential for harm is a complex and persistent challenge. Contemporary approaches frequently formalize this problem within the framework of Constrained Markov Decision Processes (CMDPs) and employ established CMDP optimization techniques. However, these methods exhibit two notable limitations. First, their reliance on reward and cost functions renders performance highly sensitive to the underlying scoring mechanism, which must capture semantic meaning rather than being triggered by superficial keywords. Second, CMDP-based training entails tuning dual-variable, a process that is both computationally expensive and does not provide any provable safety guarantee for a fixed dual variable that can be exploitable through adversarial jailbreaks. To overcome these limitations, we introduce Certifiable Safe-RLHF (CS-RLHF) that introduces a cost model trained on a large-scale corpus to assign semantically grounded safety scores. In contrast to the lagrangian-based approach, CS-RLHF adopts a rectified penalty-based formulation. This design draws on the theory of exact penalty functions in constrained optimization, wherein constraint satisfaction is enforced directly through a suitably chosen penalty term. With an appropriately scaled penalty, feasibility of the safety constraints can be guaranteed at the optimizer, eliminating the need for dual-variable updates. Empirical evaluation demonstrates that CS-RLHF outperforms state-of-the-art LLM model responses rendering at-least 5 times efficient against nominal and jail-breaking prompts

Time series reasoning is crucial to decision-making in diverse domains, including finance, energy usage, traffic, weather, and scientific discovery. While existing time series foundation models (TSFMs) can capture low-level dynamic patterns and provide accurate forecasting, further analysis usually requires additional background knowledge and sophisticated reasoning, which are lacking in most TSFMs but can be achieved through large language models (LLMs). On the other hand, without expensive post-training, LLMs often struggle with the numerical understanding of time series data. Although it is intuitive to integrate the two types of models, developing effective training recipes that align the two modalities for reasoning tasks is still an open challenge. To this end, we propose TS-Reasoner that aligns the latent representations of TSFMs with the textual inputs of LLMs for downstream understanding/reasoning tasks. Specifically, we propose a simple yet effective method to curate diverse, synthetic pairs of time series and textual captions for alignment training. We then develop a two-stage training recipe that applies instruction finetuning after the alignment pretraining. Unlike existing works that train an LLM to take time series as inputs, we leverage a pretrained TSFM and freeze it during training. Extensive experiments on several benchmarks demonstrate that TS-Reasoner not only outperforms a wide range of prevailing LLMs, Vision Language Models (VLMs), and Time Series LLMs, but also achieves this with remarkable data efficiency, e.g., using less than half the training data.

Reinforcement learning (RL) has emerged as a promising strategy for finetuning small language models (SLMs) to solve targeted tasks such as math and coding. However, RL algorithms tend to be resource-intensive, taking a significant amount of time to train. We propose RAPID, a novel RL algorithm that can substantially reduce the running time of RL. Our key insight is that RL tends to be costly due to the need to perform both inference and backpropagation during training. To maximize use of computational resources, our algorithm performs inference in large batches, and then performs off-policy policy gradient updates in mini-batches. For off-policy updates, we incorporate group advantage estimation into the policy gradient algorithm, and derive an importance weighted estimator to correct for the bias arising from off-policy learning. Our experiments demonstrate that our algorithm can reduce running time by 11%-34% on three benchmarks compared to state-of-the-art RL algorithms while maintaining similar or better accuracy.

As military organisations consider integrating large language models (LLMs) into command and control (C2) systems for planning and decision support, understanding their behavioural tendencies is critical. This study develops a benchmarking framework for evaluating aspects of legal and moral risk in targeting behaviour by comparing LLMs acting as agents in multi-turn simulated conflict. We introduce four metrics grounded in International Humanitarian Law (IHL) and military doctrine: Civilian Target Rate (CTR) and Dual-use Target Rate (DTR) assess compliance with legal targeting principles, while Mean and Max Simulated Non-combatant Casualty Value (SNCV) quantify tolerance for civilian harm. We evaluate three frontier models, GPT-4o, Gemini-2.5, and LLaMA-3.1, through 90 multi-agent, multi-turn crisis simulations across three geographic regions. Our findings reveal that off-the-shelf LLMs exhibit concerning and unpredictable targeting behaviour in simulated conflict environments. All models violated the IHL principle of distinction by targeting civilian objects, with breach rates ranging from 16.7% to 66.7%. Harm tolerance escalated through crisis simulations with MeanSNCV increasing from 16.5 in early turns to 27.7 in late turns. Significant inter-model variation emerged: LLaMA-3.1 selected an average of 3.47 civilian strikes per simulation with MeanSNCV of 28.4, while Gemini-2.5 selected 0.90 civilian strikes with MeanSNCV of 17.6. These differences indicate that model selection for deployment constitutes a choice about acceptable legal and moral risk profiles in military operations. This work seeks to provide a proof-of-concept of potential behavioural risks that could emerge from the use of LLMs in Decision Support Systems (AI DSS) as well as a reproducible benchmarking framework with interpretable metrics for standardising pre-deployment testing.

The rapid growth of the Internet of Things (IoT) has expanded opportunities for innovation but also increased exposure to botnet-driven cyberattacks. Conventional detection methods often struggle with scalability, privacy, and adaptability in resource-constrained IoT environments. To address these challenges, we present a lightweight and privacy-preserving botnet detection framework based on federated learning. This approach enables distributed devices to collaboratively train models without exchanging raw data, thus maintaining user privacy while preserving detection accuracy. A communication-efficient aggregation strategy is introduced to reduce overhead, ensuring suitability for constrained IoT networks. Experiments on benchmark IoT botnet datasets demonstrate that the framework achieves high detection accuracy while substantially reducing communication costs. These findings highlight federated learning as a practical path toward scalable, secure, and privacy-aware intrusion detection for IoT ecosystems.

Few-shot classification and meta-learning methods typically struggle to generalize across diverse domains, as most approaches focus on a single dataset, failing to transfer knowledge across various seen and unseen domains. Existing solutions often suffer from low accuracy, high computational costs, and rely on restrictive assumptions. In this paper, we introduce the notion of task-level contrastiveness, a novel approach designed to address issues of existing methods. W e start by introducing simple ways to define task augmentations, and thereafter define a task-level contrastive loss that encourages unsupervised clustering of task representations. Our method is lightweight and can be easily integrated within existing few-shot/meta-learning algorithms while providing significant benefits. Crucially, it leads to improved generalization and computational efficiency without requiring prior knowledge of task domains. W e demonstrate the effectiveness of our approach through different experiments on the MetaDataset benchmark, where it achieves superior performance without additional complexity.

Real-time animal detection and segmentation in natural environments are vital for wildlife conservation, enabling non-invasive monitoring through remote camera streams. However, these tasks remain challenging due to limited computational resources and the cryptic appearance of many species. We propose a mobile-optimized two-stage deep learning framework that integrates a Threading Detection Model (TDM) to parallelize YOLOv10-based detection and MobileSAM-based segmentation. Unlike prior YOLO+SAM pipelines, our approach improves real-time performance by reducing latency through threading. YOLOv10 handles detection while MobileSAM performs lightweight segmentation, both executed concurrently for efficient resource use. On the cryptic Houbara Bustard, a conservation-priority species, our model achieves mAP50 of 0.9627, mAP75 of 0.7731, mAP95 of 0.7178, and a MobileSAM mIoU of 0.7421. YOLOv10 operates at 43.7 ms per frame, confirming real-time readiness. We introduce a curated Houbara dataset of 40,000 annotated images to support model training and evaluation across diverse conditions. The code and dataset used in this study are publicly available on GitHub at https://github.com/LyesSaadSaoud/mobile-houbara-detseg. For interactive demos and additional resources, visit https://lyessaadsaoud.github.io/LyesSaadSaoud-Threaded-YOLO-SAM-Houbara.

Human-robot collaboration requires precise prediction of human motion over extended horizons to enable proactive collision avoidance. Unlike existing planners that rely solely on kinodynamic models, we present a prediction-driven safe planning framework that leverages granular, joint-by-joint human motion forecasting validated in a physics-based digital twin. A capsule-based artificial potential field (APF) converts these granular predictions into collision risk metrics, triggering an Adaptive RRT* (A-RRT*) planner when thresholds are exceeded. The depth camera is used to extract 3D skeletal poses and a convolutional neural network-bidirectional long short-term memory (CNN-BiLSTM) model to predict individual joint trajectories ahead of time. A digital twin model integrates real-time human posture prediction placed in front of a simulated robot to evaluate motions and physical contacts. The proposed method enables validation of planned trajectories ahead of time and bridging potential latency gaps in updating planned trajectories in real-time. In 50 trials, our method achieved 100% proactive avoidance with > 250 mm clearance and sub-2 s replanning, demonstrating superior precision and reliability compared to existing kinematic-only planners through the integration of predictive human modeling with digital twin validation.

LLM-based agents are rapidly proliferating, yet the infrastructure for discovering, evaluating, and governing them remains fragmented compared to mature ecosystems like software package registries (e.g., npm) and model hubs (e.g., Hugging Face). Recent research and engineering works have begun to consider the requisite infrastructure, but so far they focus narrowly -- on distribution, naming, or protocol negotiation. However, considering broader software engineering requirements would improve open-source distribution and ease reuse. We therefore propose AgentHub, a research agenda for agent sharing. By framing the key challenges of capability clarity, lifecycle transparency, interoperability, governance, security, and workflow integration, AgentHub charts a community-wide agenda for building reliable and scalable agent ecosystems. Our vision is a future where agents can be shared, trusted, and composed as seamlessly as today's software libraries.

Detecting anomalies in large, distributed systems presents several challenges. The first challenge arises from the sheer volume of data that needs to be processed. Flagging anomalies in a high-throughput environment calls for a careful consideration of both algorithm and system design. The second challenge comes from the heterogeneity of time-series datasets that leverage such a system in production. In practice, anomaly detection systems are rarely deployed for a single use case. Typically, there are several metrics to monitor, often across several domains (e.g. engineering, business and operations). A one-size-fits-all approach rarely works, so these systems need to be fine-tuned for every application - this is often done manually. The third challenge comes from the fact that determining the root-cause of anomalies in such settings is akin to finding a needle in a haystack. Identifying (in real time) a time-series dataset that is associated causally with the anomalous time-series data is a very difficult problem. In this paper, we describe a unified framework that addresses these challenges. Reasoning based Anomaly Detection Framework (RADF) is designed to perform real time anomaly detection on very large datasets. This framework employs a novel technique (mSelect) that automates the process of algorithm selection and hyper-parameter tuning for each use case. Finally, it incorporates a post-detection capability that allows for faster triaging and root-cause determination. Our extensive experiments demonstrate that RADF, powered by mSelect, surpasses state-of-the-art anomaly detection models in AUC performance for 5 out of 9 public benchmarking datasets. RADF achieved an AUC of over 0.85 for 7 out of 9 datasets, a distinction unmatched by any other state-of-the-art model.