Related papers: Authenticated Workflows: A Systems Approach to Pro…
Recent advances in AI agents capable of solving complex, everyday tasks, from scheduling to customer service, have enabled deployment in real-world settings, but their possibilities for unsafe behavior demands rigorous evaluation. While…
AI agents using Large Language Models (LLMs) as foundations have shown promise in solving complex real-world tasks. In this paper, we propose an LLM-based agentic workflow for automating Standard Operating Procedures (SOP). For customer…
Agentic AI systems introduce a security surface that is qualitatively different from that of stateless LLMs. They persist memory, invoke external tools, coordinate with peer agents, and operate across sessions, allowing attacks to emerge…
Our computing ecosystem is being transformed by two emerging paradigms: the increased deployment of agentic AI systems and advancements in quantum computing. With respect to agentic AI systems, one of the most critical problems is creating…
The implementation of agentic AI systems has the potential of providing more helpful AI systems in a variety of applications. These systems work autonomously towards a defined goal with reduced external control. Despite their potential, one…
AI agent protocols -- including MCP, A2A, ANP, and ACP -- enable autonomous agents to discover capabilities, delegate tasks, and compose services across trust boundaries. Despite massive deployment (MCP alone has 97M+ monthly SDK…
The emergence of Agentic AI systems has outpaced the architectural thinking required to operate them effectively. These agents differ fundamentally from traditional software: their behavior is not fixed at deployment but continuously shaped…
Vision-Language-Action (VLA) systems have shown strong potential for language-driven robotic manipulation. However, scaling them to long-horizon tasks remains challenging. Existing pipelines typically separate data collection, policy…
The rapid integration of Large Language Models (LLMs) into high-stakes domains necessitates reliable safety and compliance evaluation. However, existing static benchmarks are ill-equipped to address the dynamic nature of AI risks and…
Operating large-scale scientific facilities requires coordinating diverse subsystems, translating operator intent into precise hardware actions, and maintaining strict safety oversight. Language model-driven agents offer a natural interface…
When combining Large Language Models (LLMs) with autonomous agents, used in network monitoring and decision-making systems, this will create serious security issues. In this research, the MAESTRO framework consisting of the seven layers…
The arrival of large language models (LLMs) capable of multi-step reasoning, tool use, and long-horizon planning has produced a qualitative shift in software engineering. Where earlier code-completion tools such as GitHub Copilot operated…
Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect prompt injection. Adversaries exploit this weakness by…
AI agents increasingly require direct, structured access to application data and actions, but production deployments still struggle to express and verify the governance properties that matter in practice: least-privilege authorization,…
With AI agents increasingly deployed as long-running systems, it becomes essential to autonomously construct and continuously evolve customized software to enable interaction within dynamic environments. Yet, existing benchmarks evaluate…
Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsafe *trajectories*. We introduce **AgentFence**, an…
Advances in large language models have enabled agentic AI systems that can reason, plan, and interact with external tools to execute multi-step workflows, while public blockchains have evolved into a programmable substrate for value…
Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts. This paper presents DeepTrap, an…
Large language model (LLM) agents increasingly issue API calls that mutate real systems, yet many current architectures pass stochastic model outputs directly to execution layers. We argue that this coupling creates a safety risk because…
Agents built on LLMs are increasingly deployed across diverse domains, automating complex decision-making and task execution. However, their autonomy introduces safety risks, including security vulnerabilities, legal violations, and…