Related papers: AEGIS: No Tool Call Left Unchecked -- A Pre-Execut…
There is an increasing need for automated support for humans monitoring the activity of distributed teams of cooperating agents, both human and machine. We characterize the domain-independent challenges posed by this problem, and describe…
Artificial intelligence (AI) is increasingly being used to augment and automate cyber operations, altering the scale, speed, and accessibility of malicious activity. These shifts raise urgent questions about when AI systems introduce…
As AI agents automate critical workloads, they remain vulnerable to indirect prompt injection (IPI) attacks. Current defenses rely on monitoring protocols that jointly evaluate an agent's Chain-of-Thought (CoT) and tool-use actions to…
Human oversight of AI is promoted as a safeguard against risks such as inaccurate outputs, system malfunctions, or violations of fundamental rights, and is mandated in regulation like the European AI Act. Yet debates on human oversight have…
As Large Language Models (LLMs) and generative AI become more widespread, the content safety risks associated with their use also increase. We find a notable deficiency in high-quality content safety datasets and benchmarks that…
Static benchmarks measure what AI agents can do at a fixed point in time but not how they are adopted, maintained, or experienced in deployment. We introduce AgentPulse, a continuous evaluation framework scoring 50 agents across 10 workload…
Advanced Persistent Threats (APTs) are sophisticated multi-step attacks, planned and executed by skilled adversaries targeting modern government and enterprise networks. Intrusion Detection Systems (IDSs) and User and Entity Behavior…
Nowadays, agentic AI is emerging as a transformative paradigm for next-generation communication networks, promising to evolve large language models (LLMs) from passive chatbots into autonomous operators. However, unleashing this potential…
The rapid adoption of mobile graphical user interface (GUI) agents, which autonomously control applications and operating systems (OS), exposes new system-level attack surfaces. Existing backdoors against web GUI agents and general GenAI…
Autonomous coding agents are increasingly deployed as AI teammates in modern software engineering, independently authoring pull requests (PRs) that modify production code at scale. This study aims to systematically characterize how…
AI agents that execute tasks via tool calls frequently hallucinate results - fabricating tool executions, misstating output counts, or presenting inferences as facts. Recent approaches to verifiable AI inference rely on zero-knowledge…
Modern software engineers operate across 5-10 disconnected tools daily: GitHub, GitLab, Jira, Slack, calendar applications, CI dashboards, AI coding assistants, and container platforms. This fragmentation creates cognitive overhead that…
Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks in various domains. While these advancements promise significant…
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…
AI Agents can perform complex operations at great speed, but just like all the humans we have ever hired, their intelligence remains fallible. Miscommunications aren't noticed, systemic biases have no counter-action, and inner monologues…
AI models have become active decision makers, often acting without human supervision. The rapid advancement of AI technology has already caused harmful incidents that have hurt individuals and societies and AI unfairness in heavily…
Modern AI assistants are agentic. To answer a single user request, the underlying language model pulls in information from many sources, such as web searches, retrieved documents, tool outputs, and user follow-ups, and reasons over them…
Automating science laboratories enables faster, safer, more accurate, and more reproducible execution of protocols, accelerating the discovery and testing of new materials, drugs, and more. However, setting up and running autonomous labs…
Securing AI agents powered by Large Language Models (LLMs) represents one of the most critical challenges in AI security today. Unlike traditional software, AI agents leverage LLMs as their "brain" to autonomously perform actions via…
The April 2026 disclosure that a frontier large language model escaped its security sandbox, executed unauthorized actions, and concealed its modifications to version control history demonstrates that agentic AI systems with autonomous tool…