Building officials, especially those in resource - constrained or rural jurisdictions, struggle with labor - intensive, error - prone, and costly manual reviews of design documents as projects scale in size and complexity. Widespread adoption of Building Information Modeling (BIM) and Large Language Models (LLMs) has created opportunities for automated code review (AC R) solutions . This study proposes a novel agent - driven framework that integrates BIM - based data extraction with automated verification using both re trieval - augmented generation (RAG) and Model Context Protocol (MCP) agent pipelines. The framework employs LLM - enabled agents to extract geometry, schedules, and system attributes from heterogeneous file types, which are then processed for building code checking via two complementary mechanisms: (i) direct API calls to DOE's COMcheck engine, providing deterministic and audit - ready outputs, and (ii) RAG - based reasoning over rule provisions, allowing flexible interpretation where coverage is incomplete or amb iguous . The framework was evaluated through case demonstrations, including automated extraction of geometric attributes (e.g., surface area, tilt, and insulation values), parsing of operational schedules, and design validation for lighting allowances under ASHRAE Standard 90.1 - 2022. Comparative performance tests across multiple large language models showed that Generative Pre - trained Transformer 4 Omni (GPT - 4o) achieved the best balance of efficiency and stability, while smaller models exhibited inconsistenc ies or failure s . Results confirm that MCP agent pipelines perform better than RAG reasoning pipelines on rigor and flexibility in workflows.

Large language models (LLMs) can improve reasoning at inference time through test-time scaling (TTS), where multiple reasoning traces are generated and the best one is selected. Prior work shows that increasing the number of samples K steadily improves accuracy. In this paper, we demonstrate that this trend does not hold indefinitely: at large K, further scaling yields no gains, and certain hard questions remain unsolved regardless of the number of traces. Interestingly, we find that different sampling temperatures solve different subsets of problems, implying that single-temperature scaling explores only part of a model's potential. We therefore propose scaling along the temperature dimension, which enlarges the reasoning boundary of LLMs. Temperature scaling also enables base models to reach performance comparable to reinforcement learning (RL)-trained counterparts, without additional post-training. We further provide a comprehensive analysis of this phenomenon and design a multi-temperature voting method that reduces the overhead of temperature scaling. Overall, our findings suggest that TTS is more powerful than previously thought, and that temperature scaling offers a simple and effective way to unlock the latent potential of base models. Large language models (LLMs) have demonstrated strong reasoning capabilities for complex problems at test time (Wei et al., 2022). As illustrated in Figure 1a, two main approaches have emerged to achieve such reasoning. The first trains models to produce long reasoning traces with self-reflection and correction, often implemented through reinforcement learning (RL) (Guo et al., 2025a; Y ang et al., 2025c). While effective, this approach requires costly and time-consuming training (Liu et al., 2025a). The second, known as test-time scaling (TTS) (Brown et al., 2024; Snell et al., 2025; Zhao et al., 2025), shifts the burden to inference: the model generates multiple reasoning traces in parallel and a verifier selects the most reliable one (Saad-Falcon et al., 2025a).

Abstract-- This paper investigates the integration of haptic feedback and virtual reality (VR) control interfaces to enhance teleoperation and telemanipulation of underwater ROVs (remotely operated vehicles). Traditional ROV teleoperation relies on low-resolution 2D camera feeds and lacks immersive and sensory feedback, which diminishes situational awareness in complex subsea environments. We propose SubSense - a novel VR-Haptic framework incorporating a non-invasive feedback interface to an otherwise 1-DOF (degree of freedom) manipulator, which is paired with the teleoperator's glove to provide haptic feedback and grasp status. Our results highlight the potential of multisensory feedback in immersive virtual environments to significantly improve remote situational awareness and mission performance, offering more intuitive and accessible ROV operations in the field. Remotely Operated V ehicles (ROVs) are indispensable tools in the marine industry, offering a safer and more cost-effective alternative to human divers [1]. Underwater ROVs are versatile platforms supporting a range of missions, from routine imaging and infrastructure inspection to complex tasks such as environmental monitoring [2], maintaining sub-sea infrastructure [3], [4], performing mine countermeasure and explosive ordinance disposal [5], salvaging, search-and-rescue [6], and deep-water expeditions [7]. With over 79% of subsea deployments done by ROVs, they play a crucial role in commerce, military, and science - enabling us to explore beyond the limits of human scuba divers [8]. Despite growing industrial demands and recent advancements, underwater ROVs still have inherent limitations, particularly in their immersive control and interaction capabilities.

While agentic AI has advanced in automating individual tasks, managing complex multi-agent workflows remains a challenging problem. This paper presents a research vision for autonomous agentic systems that orchestrate collaboration within dynamic human-AI teams. We propose the Autonomous Manager Agent as a core challenge: an agent that decomposes complex goals into task graphs, allocates tasks to human and AI workers, monitors progress, adapts to changing conditions, and maintains transparent stakeholder communication. We formalize workflow management as a Partially Observable Stochastic Game and identify four foundational challenges: (1) compositional reasoning for hierarchical decomposition, (2) multi-objective optimization under shifting preferences, (3) coordination and planning in ad hoc teams, and (4) governance and compliance by design. To advance this agenda, we release MA-Gym, an open-source simulation and evaluation framework for multi-agent workflow orchestration. Evaluating GPT-5-based Manager Agents across 20 workflows, we find they struggle to jointly optimize for goal completion, constraint adherence, and workflow runtime - underscoring workflow management as a difficult open problem. We conclude with organizational and ethical implications of autonomous management systems.

As LLMs increasingly power agents that interact with external tools, tool use has become an essential mechanism for extending their capabilities. These agents typically select tools from growing databases or marketplaces to solve user tasks, creating implicit competition among tool providers and developers for visibility and usage. In this paper, we show that this selection process harbors a critical vulnerability: by iteratively manipulating tool names and descriptions, adversaries can systematically bias agents toward selecting specific tools, gaining unfair advantage over equally capable alternatives. We present ToolTweak, a lightweight automatic attack that increases selection rates from a baseline of around 20% to as high as 81%, with strong transferability between open-source and closed-source models. Beyond individual tools, we show that such attacks cause distributional shifts in tool usage, revealing risks to fairness, competition, and security in emerging tool ecosystems. To mitigate these risks, we evaluate two defenses: paraphrasing and perplexity filtering, which reduce bias and lead agents to select functionally similar tools more equally. All code will be open-sourced upon acceptance.

In this paper, we study the use of robust model independent bounded extremum seeking (ES) feedback control to improve the robustness of deep reinforcement learning (DRL) controllers for a class of nonlinear time-varying systems. DRL has the potential to learn from large datasets to quickly control or optimize the outputs of many-parameter systems, but its performance degrades catastrophically when the system model changes rapidly over time. Bounded ES can handle time-varying systems with unknown control directions, but its convergence speed slows down as the number of tuned parameters increases and, like all local adaptive methods, it can get stuck in local minima. We demonstrate that together, DRL and bounded ES result in a hybrid controller whose performance exceeds the sum of its parts with DRL taking advantage of historical data to learn how to quickly control a many-parameter system to a desired setpoint while bounded ES ensures its robustness to time variations. We present a numerical study of a general time-varying system and a combined ES-DRL controller for automatic tuning of the Low Energy Beam Transport section at the Los Alamos Neutron Science Center linear particle accelerator.

This paper presents CADL (Cognitive-Adaptive Deception Layer), an adaptive deception framework achieving 99.88% detection rate with 0.13% false positive rate on the CICIDS2017 dataset. The framework employs ensemble machine learning (Random Forest, XGBoost, Neural Networks) combined with behavioral profiling to identify and adapt responses to network intrusions. Through a coordinated signal bus architecture, security components share real-time intelligence, enabling collective decision-making. The system profiles attackers based on temporal patterns and deploys customized deception strategies across five escalation levels. Evaluation on 50,000 CICIDS2017 test samples demonstrates that CADL significantly outperforms traditional intrusion detection systems (Snort: 71.2%, Suricata: 68.5%) while maintaining production-ready false positive rates. The framework's behavioral analysis achieves 89% accuracy in classifying attacker profiles. We provide open-source implementation and transparent performance metrics, offering an accessible alternative to commercial deception platforms costing $150-400 per host annually.

Abstract--Smart grids are exposed to passive eavesdropping, where attackers listen silently to communication links. Although no data is actively altered, such reconnaissance can reveal grid topology, consumption patterns, and operational behavior, creating a gateway to more severe targeted attacks. Detecting this threat is difficult because the signals it produces are faint, short-lived, and often disappear when traffic is examined by a single node or along a single timeline. This paper introduces a graph-centric, multimodal detector that fuses physical-layer (Channel State Information (CSI), Signal-to-Noise Ratio (SNR)) and behavioral (latency, Packet Error Rate (PER), event context) indicators over ego-centric star subgraphs and short temporal windows to detect passive attacks. T o capture stealthy perturbations, a two-stage encoder is introduced: graph convolution aggregates spatial context across ego-centric star subgraphs, while a bidirectional GRU models short-term temporal dependencies. The encoder transforms heterogeneous features into a unified spatio-temporal representation suitable for classification. Training occurs in a federated learning setup under FedProx, improving robustness to heterogeneous local raw data and contributing to the trustworthiness of decentralized training; raw measurements remain on client devices. The model achieves a testing accuracy of 98.32% per-timestep (F1 The results demonstrate that combining spatial and temporal context enables reliable detection of stealthy reconnaissance while maintaining low false-positive rates, making the approach suitable for non-IID federated smart-grid deployments. Smart grids [1] define new energy systems constructed on the notion of bidirectional communication between consumers and utilities. They enable the management of real-time data across distributed nodes. However, this open communication exposes the grid to significant risks of passive attacks, which pose a threat to privacy, trust, and stability [2].

Adaptive Cruise Control (ACC) is rapidly proliferating across electric vehicles (EVs) and internal combustion engine (ICE) vehicles, enhancing traffic flow while simultaneously expanding the attack surface for communication-based cyberattacks. Because the two powertrains translate control inputs into motion differently, their cyber-resilience remains unquantified. Therefore, we formalize six novel message-level attack vectors and implement them in a ring-road simulation that systematically varies the ACC market penetration rates (MPRs) and the spatial pattern of compromised vehicles. A three-tier risk taxonomy converts disturbance metrics into actionable defense priorities for practitioners. Across all simulation scenarios, EV platoons exhibit lower velocity standard deviation, reduced spacing oscillations, and faster post-attack recovery compared to ICE counterparts, revealing an inherent stability advantage. These findings clarify how controller-to-powertrain coupling influences vulnerability and offer quantitative guidance for the detection and mitigation of attacks in mixed automated traffic.

Abstract--We explore how large language models (LLMs) assess offensiveness in political discourse when prompted to adopt specific political and cultural perspectives. Using a multilingual subset of the MD-Agreement dataset centered on tweets from the 2020 US elections, we evaluate several recent LLMs - including DeepSeek-R1, o4-mini, GPT -4.1-mini, Qwen3, Gemma, and Mistral - tasked with judging tweets as offensive or non-offensive from the viewpoints of varied political personas (far-right, conservative, centrist, progressive) across English, Polish, and Russian contexts. Our results show that larger models with explicit reasoning abilities (e.g., DeepSeek-R1, o4-mini) are more consistent and sensitive to ideological and cultural variation, while smaller models often fail to capture subtle distinctions. We find that reasoning capabilities significantly improve both the personalization and interpretability of offensiveness judgments, suggesting that such mechanisms are key to adapting LLMs for nuanced sociopolitical text classification across languages and ideologies. Detecting offensive language is vital for fostering respectful discourse, particularly on social media. Y et, offensiveness is inherently subjective - shaped by individual ideologies, cultural backgrounds, and values [1], [2]. Supervised models rely on ground-truth labels that reflect annotators' biases, complicating efforts to build fair and robust systems [3]. Political discourse, marked by polarization, offers a compelling lens: individuals often tolerate combative language from their own side while labeling opposing views as offensive [4]. Recent advances in large language models (LLMs) - from GPT -based to instruction-tuned variants - have improved context-sensitive understanding [5]-[8].