Reinforcement learning agents often behave unexpectedly in sparse-reward or safety-critical environments, creating a strong need for reliable debugging and verification tools. In this paper, we propose STACHE, a comprehensive framework for generating local, black-box explanations for an agent's specific action within discrete Markov games. Our method produces a Composite Explanation consisting of two complementary components: (1) a Robustness Region, the connected neighborhood of states where the agent's action remains invariant, and (2) Minimal Counterfactuals, the smallest state perturbations required to alter that decision. By exploiting the structure of factored state spaces, we introduce an exact, search-based algorithm that circumvents the fidelity gaps of surrogate models. Empirical validation on Gymnasium environments demonstrates that our framework not only explains policy actions, but also effectively captures the evolution of policy logic during training - from erratic, unstable behavior to optimized, robust strategies - providing actionable insights into agent sensitivity and decision boundaries.

Abstract--The integration of Unmanned Aerial V ehicles (UA Vs) and Unmanned Ground V ehicles (UGVs) is increasingly central to the development of intelligent autonomous systems for applications such as search and rescue, environmental monitoring, and logistics. However, precise coordination between these platforms in real-time scenarios presents major challenges, particularly when external localization infrastructure such as GPS or GNSS is unavailable or degraded [1]. This paper proposes a vision-based, data-driven framework for real-time UA V-UGV integration, with a focus on robust UGV detection and heading angle prediction for navigation and coordination. The system employs a fine-tuned YOLOv5 model to detect UGVs and extract bounding box features, which are then used by a lightweight artificial neural network (ANN) to estimate the UA V's required heading angle. A VICON motion capture system was used to generate ground-truth data during training, resulting in a dataset of over 13,000 annotated images collected in a controlled lab environment. The trained ANN achieves a mean absolute error of 0.1506 and a root mean squared error of 0.1957, offering accurate heading angle predictions using only monocular camera inputs. Experimental evaluations achieve 95% accuracy in UGV detection. This work contributes a vision-based, infrastructure-independent solution that demonstrates strong potential for deployment in GPS/GNSS-denied environments, supporting reliable multi-agent coordination under realistic dynamic conditions. A demonstration video showcasing the system's real-time performance, including UGV detection, heading angle prediction, and UA V alignment under dynamic conditions, is available at: https://github.com/Kooroshraf/UA HE integration of Unmanned Aerial V ehicles (UA Vs) and Unmanned Ground V ehicles (UGVs) has emerged as a powerful paradigm in multi-agent systems, offering significant advantages for surveillance, search and rescue, precision agriculture, and autonomous logistics [2]. UA Vs provide agility and a wide field of view, while UGVs offer stable ground-level interaction and payload capacity.

Long-term planning in complex, text-based environments presents significant challenges due to open-ended action spaces, ambiguous observations, and sparse feedback. Recent research suggests that large language models (LLMs) encode rich semantic knowledge about the world, which can be valuable for guiding agents in high-level reasoning and planning across both embodied and purely textual settings. However, existing approaches often depend heavily on querying LLMs during training and inference, making them computationally expensive and difficult to deploy efficiently. In addition, these methods typically employ a pretrained, unaltered LLM whose parameters remain fixed throughout training, providing no opportunity for adaptation to the target task. To address these limitations, we introduce SCOPE (Subgoal-COnditioned Pretraining for Efficient planning), a one-shot hierarchical planner that leverages LLM-generated subgoals only at initialization to pretrain a lightweight student model. Unlike prior approaches that distill LLM knowledge by repeatedly prompting the model to adaptively generate subgoals during training, our method derives subgoals directly from example trajectories. This design removes the need for repeated LLM queries, significantly improving efficiency, though at the cost of reduced explainability and potentially suboptimal subgoals. Despite their suboptimality, our results on the TextCraft environment show that LLM-generated subgoals can still serve as a strong starting point for hierarchical goal decomposition in text-based planning tasks. Compared to the LLM-based hierarchical agent ADaPT (Prasad et al., 2024), which achieves a 0.52 success rate, our method reaches 0.56 and reduces inference time from 164.4 seconds to just 3.0 seconds.

Metadata vocabularies are essential for advancing FAIR and FARR data principles, but their development constrained by limited human resources and inconsistent standardization practices. This paper introduces MatSci-YAMZ, a platform that integrates artificial intelligence (AI) and human-in-the-loop (HILT), including crowdsourcing, to support metadata vocabulary development. The paper reports on a proof-of-concept use case evaluating the AI-HILT model in materials science, a highly interdisciplinary domain Six (6) participants affiliated with the NSF Institute for Data-Driven Dynamical Design (ID4) engaged with the MatSci-YAMZ plaform over several weeks, contributing term definitions and providing examples to prompt the AI-definitions refinement. Nineteen (19) AI-generated definitions were successfully created, with iterative feedback loops demonstrating the feasibility of AI-HILT refinement. Findings confirm the feasibility AI-HILT model highlighting 1) a successful proof of concept, 2) alignment with FAIR and open-science principles, 3) a research protocol to guide future studies, and 4) the potential for scalability across domains. Overall, MatSci-YAMZ's underlying model has the capacity to enhance semantic transparency and reduce time required for consensus building and metadata vocabulary development.

Recent advances in protein language models (PLMs) have demonstrated remarkable capabilities in understanding protein sequences. However, the extent to which different model architectures capture antibody-specific biological properties remains unexplored. In this work, we systematically investigate how architectural choices in PLMs influence their ability to comprehend antibody sequence characteristics and functions. We evaluate three state-of-the-art PLMs-AntiBERTa, BioBERT, and ESM2--against a general-purpose language model (GPT-2) baseline on antibody target specificity prediction tasks. Our results demonstrate that while all PLMs achieve high classification accuracy, they exhibit distinct biases in capturing biological features such as V gene usage, somatic hypermutation patterns, and isotype information. Through attention attribution analysis, we show that antibody-specific models like AntiBERTa naturally learn to focus on complementarity-determining regions (CDRs), while general protein models benefit significantly from explicit CDR-focused training strategies. These findings provide insights into the relationship between model architecture and biological feature extraction, offering valuable guidance for future PLM development in computational antibody design.

Knowledge Distillation (KD) has emerged as a promising technique for model compression but faces critical limitations: (1) sensitivity to hyperparameters requiring extensive manual tuning, (2) capacity gap when distilling from very large teachers to small students, (3) suboptimal coordination in multi-teacher scenarios, and (4) inefficient use of computational resources. We present \textbf{HPM-KD}, a framework that integrates six synergistic components: (i) Adaptive Configuration Manager via meta-learning that eliminates manual hyperparameter tuning, (ii) Progressive Distillation Chain with automatically determined intermediate models, (iii) Attention-Weighted Multi-Teacher Ensemble that learns dynamic per-sample weights, (iv) Meta-Learned Temperature Scheduler that adapts temperature throughout training, (v) Parallel Processing Pipeline with intelligent load balancing, and (vi) Shared Optimization Memory for cross-experiment reuse. Experiments on CIFAR-10, CIFAR-100, and tabular datasets demonstrate that HPM-KD: achieves 10x-15x compression while maintaining 85% accuracy retention, eliminates the need for manual tuning, and reduces training time by 30-40% via parallelization. Ablation studies confirm independent contribution of each component (0.10-0.98 pp). HPM-KD is available as part of the open-source DeepBridge library.

We present the first comprehensive evaluation of AI agents against human cybersecurity professionals in a live enterprise environment. We evaluate ten cybersecurity professionals alongside six existing AI agents and ARTEMIS, our new agent scaffold, on a large university network consisting of ~8,000 hosts across 12 subnets. ARTEMIS is a multi-agent framework featuring dynamic prompt generation, arbitrary sub-agents, and automatic vulnerability triaging. In our comparative study, ARTEMIS placed second overall, discovering 9 valid vulnerabilities with an 82% valid submission rate and outperforming 9 of 10 human participants. While existing scaffolds such as Codex and CyAgent underperformed relative to most human participants, ARTEMIS demonstrated technical sophistication and submission quality comparable to the strongest participants. We observe that AI agents offer advantages in systematic enumeration, parallel exploitation, and cost -- certain ARTEMIS variants cost $18/hour versus $60/hour for professional penetration testers. We also identify key capability gaps: AI agents exhibit higher false-positive rates and struggle with GUI-based tasks.

Abstract--Generative Artificial Intelligence Models like Large Language Models (LLMs) and Large Vision Models (VLMs) exhibit state-of-the-art performance across a wide range of tasks but remain vulnerable to hardware-based threats, specifically bit-flip attacks (BF As), posing a serious risk to their security in safety-critical applications. Existing BF A discovery methods--gradient-based, static analysis, and search-based--lack generalizability and struggle to scale, often failing to analyze the vast parameter space and complex interdependencies of modern foundation models in a reasonable time. This paper proposes FlipLLM, a reinforcement learning (RL) architecture-agnostic framework that formulates BF A discovery as a sequential decision-making problem. FlipLLM combines sensitivity-guided layer pruning with Q-learning to efficiently identify minimal, high-impact bit sets capable of inducing catastrophic failure. We demonstrate the effectiveness and generalizability of FlipLLM by applying it to a diverse set of models, including prominent text-only LLMs (GPT -2 Large, LLaMA 3.1 8B, and DeepSeek-V2 7B), VLMs such as LLaV A 1.6, and datasets, such as MMLU, MMLU-Pro, VQA v2, and T extVQA. Our results show that FlipLLM can identify critical bits that are vulnerable to BF As up to 2.5 faster than SOT A methods. We demonstrate that flipping the FlipLLM-identified bits plummets the accuracy of LLaMA 3.1 8B from 69.9% to 0.2%, and for LLaV A's VQA score from 78% to almost 0%, by flipping as few as 5 and 7 bits, respectively. Further analysis shows that applying standard hardware protection mechanisms, such as ECC SECDED, to the FlipLLM-identified bit locations completely mitigates the BF A impact, demonstrating the practical value of our framework for guiding hardware-level defenses. FlipLLM offers the first scalable and adaptive methodology for exploring the BF A vulnerability of both language and multimodal foundation models, paving the way for comprehensive hardware-security evaluation. Generative Artificial Intelligence models like Large Language Models (LLMs) [1] and Large Vision Models (VLMs) represent a transformative advancement in artificial intelligence, finding integration into mission-critical systems spanning healthcare, finance, and autonomous navigation [2], [3]. Their effective deployment mandates reliable and secure operation across diverse hardware infrastructures, from expansive cloud accelerators to resource-constrained edge devices.

Robotic manipulation requires both rich multimodal perception and effective learning frameworks to handle complex real-world tasks. See-through-skin (STS) sensors, which combine tactile and visual perception, offer promising sensing capabilities, while modern imitation learning provides powerful tools for policy acquisition. However, existing STS designs lack simultaneous multimodal perception and suffer from unreliable tactile tracking. Furthermore, integrating these rich multimodal signals into learning-based manipulation pipelines remains an open challenge. We introduce TacThru, an STS sensor enabling simultaneous visual perception and robust tactile signal extraction, and TacThru-UMI, an imitation learning framework that leverages these multimodal signals for manipulation. Our sensor features a fully transparent elastomer, persistent illumination, novel keyline markers, and efficient tracking, while our learning system integrates these signals through a Transformer-based Diffusion Policy. Experiments on five challenging real-world tasks show that TacThru-UMI achieves an average success rate of 85.5%, significantly outperforming the baselines of alternating tactile-visual (66.3%) and vision-only (55.4%). The system excels in critical scenarios, including contact detection with thin and soft objects and precision manipulation requiring multimodal coordination. This work demonstrates that combining simultaneous multimodal perception with modern learning frameworks enables more precise, adaptable robotic manipulation.

California's wildfire season keeps getting worse over the years, overwhelming the emergency response teams. These fires cause massive destruction to both property and human life. Because of these reasons, there's a growing need for accurate and practical predictions that can help assist with resources allocation for the Wildfire managers or the response teams. In this research, we built machine learning models to predict the number of days it will require to fully contain a wildfire in California. Here, we addressed an important gap in the current literature. Most prior research has concentrated on wildfire risk or how fires spread, and the few that examine the duration typically predict it in broader categories rather than a continuous measure. This research treats the wildfire duration prediction as a regression task, which allows for more detailed and precise forecasts rather than just the broader categorical predictions used in prior work. We built the models by combining three publicly available datasets from California Department of Forestry and Fire Protection's Fire and Resource Assessment Program (FRAP). This study compared the performance of baseline ensemble regressor, Random Forest and XGBoost, with a Long Short-Term Memory (LSTM) neural network. The results show that the XGBoost model slightly outperforms the Random Forest model, likely due to its superior handling of static features in the dataset. The LSTM model, on the other hand, performed worse than the ensemble models because the dataset lacked temporal features. Overall, this study shows that, depending on the feature availability, Wildfire managers or Fire management authorities can select the most appropriate model to accurately predict wildfire containment duration and allocate resources effectively.