Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse applications, yet they pose significant security risks that threaten their safe deployment in critical domains. Current security alignment methodologies predominantly rely on Process Reward Models (PRMs) to evaluate intermediate reasoning steps, introducing substantial computational overhead and scalability constraints. This paper presents a novel PRM-free security alignment framework that leverages automated red teaming and adversarial training to achieve robust security guarantees while maintaining computational efficiency. Our approach systematically identifies vulnerabilities through sophisticated attack strategies including genetic algorithm optimization, multi-agent simulation, and advanced prompt mutation techniques. The framework enhances model robustness via targeted adversarial training with curriculum learning and adaptive regularization mechanisms. Comprehensive experimental evaluation across five state-of-the-art LLMs demonstrates that our method achieves superior security alignment performance compared to PRM-based approaches while reducing computational costs by 61\%. The framework incorporates transparent reporting and continuous audit mechanisms that enable iterative security improvement and regulatory compliance. Our contributions advance the field of efficient LLM security alignment by democratizing access to robust security measures for resource-constrained organizations and providing a scalable foundation for addressing evolving adversarial threats.

In 2023, satellite and mobile networks crossed a historic threshold: standard smartphones, using unmodified 3GPP protocols, connected directly to low Earth orbit (LEO) satellites. This first wave of direct-to-device (D2D) demonstrations validated the physical feasibility of satellite-based mobile access. However, these systems remain fallback-grade--rural-only, bandwidth-limited, and fully dependent on Earth-based mobile cores for identity, session, and policy control. This paper asks a more ambitious question: Can a complete mobile network, including radio access, core functions, traffic routing, and content delivery, operate entirely from orbit? And can it deliver sustained, urban-grade service in the world's densest cities? We present the first end-to-end system architecture for a fully orbital telco, integrating electronically steered phased arrays with 1000-beam capacity, space-based deployment of 5G core functions (UPF, AMF), and inter-satellite laser mesh backhaul. We analyze spectral efficiency, beam capacity, and link budgets under dense urban conditions, accounting for path loss, Doppler, and multipath. Simulations show that rooftop and line-of-sight users can sustain 64-QAM throughput, while street-level access is feasible with relay or assisted beam modes. The paper outlines the remaining constraints, power, thermal dissipation, compute radiation hardening, and regulatory models, and demonstrates that these are engineering bottlenecks, not physical limits. Finally, we propose a staged 15-year roadmap from today's fallback D2D systems to autonomous orbital overlays delivering 50-100 Mbps to handhelds in megacities, with zero reliance on terrestrial infrastructure.

In the age of AI, human commanders need to use the computational powers available in today's environment to simulate a very large number of scenarios. Within each scenario, situations occur where different decision design options could have ethical consequences. Making these decisions reliant on human judgement is both counter-productive to the aim of exploring very large number of scenarios in a timely manner and infeasible when considering the workload needed to involve humans in each of these choices. In this paper, we move human judgement outside the simulation decision cycle. Basically, the human will design the ethical metric space, leaving it to the simulated environment to explore the space. When the simulation completes its testing cycles, the testing environment will come back to the human commander with a few options to select from. The human commander will then exercise human-judgement to select the most appropriate course of action, which will then get executed accordingly. We assume that the problem of designing metrics that are sufficiently granular to assess the ethical implications of decisions is solved. Subsequently, the fundamental problem we look at in this paper is how to weight ethical decisions during the running of these simulations; that is, how to dynamically weight the ethical attributes when agents are faced with decision options with ethical implications during generative simulations. The multi-criteria decision making literature has started to look at nearby problems, where the concept of entropy has been used to determine the weights during aggregation. We draw from that literature different approaches to automatically calculate the weights for ethical attributes during simulation-based testing and evaluation.

Every day, multinational firms process thousands of transactions, each of which must adhere to tax regulations that vary by jurisdiction and are often nuanced. The determination of product and service tax codes, such as HSN or SAC is a major use case in Tax compliance. An accurate determination of such codes is imperative to avoid any tax penalties. This paper proposes a domain-adaptive small language model (SLM) with an encoder-decoder architecture for the enhanced prediction of product and service tax codes. In this approach, we address the problem of predicting hierarchical tax code sequences using unstructured product and services data. We employ an SLM based upon encoder-decoder architecture as this enables sequential generation of tax codes to capture the hierarchical dependencies present within the tax codes. Our experiments demonstrate that encoder-decoder SLMs can be successfully applied to the sequential prediction of structured tax codes, a domain that remains comparatively unexplored in current NLP research. In this paper, we demonstrate the superior performance of the domain-adaptive encoder-decoder SLMs over flat classifiers when applied to the Harmonized System of Nomenclature (HSN), and achieve superior results compared to decoder-only and encoder-only architectures for structured sequence generation tasks. This approach can also be scaled to other government-mandated tax commodity codes, such as United Nations Standard Products and Services Codes (UNSPSC), or Brazil's Nomenclatura Comum do Mercosul (NCM).

Blind and low vision (BLV) individuals use Generative AI (GenAI) tools to interpret and manage visual content in their daily lives. While such tools can enhance the accessibility of visual content and so enable greater user independence, they also introduce complex challenges around visual privacy. In this paper, we investigate the current practices and future design preferences of blind and low vision individuals through an interview study with 21 participants. Our findings reveal a range of current practices with GenAI that balance privacy, efficiency, and emotional agency, with users accounting for privacy risks across six key scenarios, such as self-presentation, indoor/outdoor spatial privacy, social sharing, and handling professional content. Our findings reveal design preferences, including on-device processing, zero-retention guarantees, sensitive content redaction, privacy-aware appearance indicators, and multimodal tactile mirrored interaction methods. We conclude with actionable design recommendations to support user-centered visual privacy through GenAI, expanding the notion of privacy and responsible handling of others data.

Recent advances in generative AI have led to remarkable interest in using systems that rely on large language models (LLMs) for practical applications. However, meaningful evaluation of these systems in real-world scenarios comes with a distinct set of challenges, which are not well-addressed by synthetic benchmarks and de-facto metrics that are often seen in the literature. We present a practical evaluation framework which outlines how to proactively curate representative datasets, select meaningful evaluation metrics, and employ meaningful evaluation methodologies that integrate well with practical development and deployment of LLM-reliant systems that must adhere to real-world requirements and meet user-facing needs.

Recent advancements in LLMs indicate potential for novel applications, as evidenced by the reasoning capabilities in the latest OpenAI and DeepSeek models. To apply these models to domain-specific applications beyond text generation, LLM-based multi-agent systems can be utilized to solve complex tasks, particularly by combining reasoning techniques, code generation, and software execution across multiple, potentially specialized LLMs. However, while many evaluations are performed on LLMs, reasoning techniques, and applications individually, their joint specification and combined application are not well understood. Defined specifications for multi-agent LLM systems are required to explore their potential and suitability for specific applications, allowing for systematic evaluations of LLMs, reasoning techniques, and related aspects. This paper reports the results of exploratory research on (1.) multi-agent specification by introducing an agent schema language and (2.) the execution and evaluation of the specifications through a multi-agent system architecture and prototype. The specification language, system architecture, and prototype are first presented in this work, building on an LLM system from prior research. Test cases involving cybersecurity tasks indicate the feasibility of the architecture and evaluation approach. As a result, evaluations could be demonstrated for question answering, server security, and network security tasks completed correctly by agents with LLMs from OpenAI and DeepSeek.

We analyze the extent to which internal representations of language models (LMs) identify and distinguish mentions of named entities, focusing on the many-to-many correspondence between entities and their mentions. We first formulate two problems of entity mentions -- ambiguity and variability -- and propose a framework analogous to clustering quality metrics. Specifically, we quantify through cluster analysis of LM internal representations the extent to which mentions of the same entity cluster together and mentions of different entities remain separated. Our experiments examine five Transformer-based autoregressive models, showing that they effectively identify and distinguish entities with metrics analogous to precision and recall ranging from 0.66 to 0.9. Further analysis reveals that entity-related information is compactly represented in a low-dimensional linear subspace at early LM layers. Additionally, we clarify how the characteristics of entity representations influence word prediction performance. These findings are interpreted through the lens of isomorphism between LM representations and entity-centric knowledge structures in the real world, providing insights into how LMs internally organize and use entity information.

Fast and effective incident response is essential to prevent adversarial cyberattacks. Autonomous Cyber Defense (ACD) aims to automate incident response through Artificial Intelligence (AI) agents that plan and execute actions. Most ACD approaches focus on single-agent scenarios and leverage Reinforcement Learning (RL). However, ACD RL-trained agents depend on costly training, and their reasoning is not always explainable or transferable. Large Language Models (LLMs) can address these concerns by providing explainable actions in general security contexts. Researchers have explored LLM agents for ACD but have not evaluated them on multi-agent scenarios or interacting with other ACD agents. In this paper, we show the first study on how LLMs perform in multi-agent ACD environments by proposing a new integration to the CybORG CAGE 4 environment. We examine how ACD teams of LLM and RL agents can interact by proposing a novel communication protocol. Our results highlight the strengths and weaknesses of LLMs and RL and help us identify promising research directions to create, train, and deploy future teams of ACD agents.

Manus AI is a general-purpose AI agent introduced in early 2025, marking a significant advancement in autonomous artificial intelligence. Developed by the Chinese startup Monica.im, Manus is designed to bridge the gap between "mind" and "hand" - combining the reasoning and planning capabilities of large language models with the ability to execute complex, end-to-end tasks that produce tangible outcomes. This paper presents a comprehensive overview of Manus AI, exploring its core technical architecture, diverse applications across sectors such as healthcare, finance, manufacturing, robotics, and gaming, as well as its key strengths, current limitations, and future potential. Positioned as a preview of what lies ahead, Manus AI represents a shift toward intelligent agents that can translate high-level intentions into real-world actions, heralding a new era of human-AI collaboration.