Related papers: NuHF Claw: A Risk Constrained Cognitive Agent Fram…
The potential for advances in information-age technologies to undermine nuclear deterrence and influence the potential for nuclear escalation represents a critical question for international politics. One challenge is that uncertainty about…
Computer-use agents (CUAs) can now autonomously complete complex tasks in real digital environments, but when misled, they can also be used to automate harmful actions programmatically. Existing safety evaluations largely target explicit…
Recently, AI-driven interactions with computing devices have advanced from basic prototype tools to sophisticated, LLM-based systems that emulate human-like operations in graphical user interfaces. We are now witnessing the emergence of…
Current AI agent frameworks have made remarkable progress in automating individual tasks, yet all existing systems serve a single user. Human productivity rests on the social and organizational relationships through which people coordinate,…
The safety of autonomous AI agents is increasingly recognized as a critical open problem. As agents transition from passive text generators to active actors capable of executing shell commands, modifying files, calling APIs, and browsing…
As the size and complexity of software systems increase, the number and sophistication of software security flaws increase as well. The analysis of these flaws began as a manual approach, but it soon became apparent that tools were…
Large language model (LLM)-based computer-use agents represent a convergence of AI and OS capabilities, enabling natural language to control system- and application-level functions. However, due to LLMs' inherent uncertainty issues,…
Conventional reinforcement learning (RL) approaches often struggle to learn effective policies under sparse reward conditions, necessitating the manual design of complex, task-specific reward functions. To address this limitation,…
Digitalization in nuclear power plant (NPP) control rooms is reshaping how operators interact with procedures and interface elements. However, existing computer-based procedures (CBPs) often lack semantic integration with human-system…
Robots operating in real world settings must navigate and maintain safety while interacting with many heterogeneous agents and obstacles. Multi-Agent Control Barrier Functions (CBF) have emerged as a computationally efficient tool to…
Risk management resulting from the actions and states of the different elements making up a operating room is a major concern during a surgical procedure. Agent-based simulation shows an interest through its interaction concepts,…
As AI systems increasingly influence critical decisions, they face threats that exploit reasoning mechanisms rather than technical infrastructure. We present a framework for cognitive cybersecurity, a systematic protection of AI reasoning…
This work introduces a human-inspired reinforcement learning (RL) architecture that integrates Pavlovian and instrumental processes to enhance decision-making in autonomous systems. While existing engineering solutions rely almost…
Complex human activity recognition (CHAR) remains a pivotal challenge within ubiquitous computing, especially in the context of smart environments. Existing studies typically require meticulous labeling of both atomic and complex…
As Large Language Models (LLMs) continue to be increasingly applied across various domains, their widespread adoption necessitates rigorous monitoring to prevent unintended negative consequences and ensure robustness. Furthermore, LLMs must…
The rapid deployment of large language model (LLM)-based agents introduces a new class of risks, driven by their capacity for autonomous planning, multi-step tool integration, and emergent interactions. It raises some risk factors for…
LLM-based multi-agent systems (MASs) are transforming personal productivity by autonomously executing complex, cross-platform tasks. Frameworks such as OpenClaw demonstrate the potential of locally deployed agents integrated with personal…
Nuclear waste management requires rigorous regulatory compliance assessment, demanding advanced decision-support systems capable of addressing complex legal, environmental, and safety considerations. This paper presents a multi-agent…
The inherent non-deterministic nature of autonomous agents, particularly within low-code/no-code (LCNC) environments, presents significant reliability challenges. Agents can become trapped in unforeseen loops, generate inaccurate outputs,…
The emergence of autonomous Large Language Model (LLM) agents capable of tool usage has introduced new safety risks that go beyond traditional conversational misuse. These agents, empowered to execute external functions, are vulnerable to…