Related papers: Security Considerations for Artificial Intelligenc…
We formalize three design axioms for sustained adoption of agent-centric AI systems executing multi-step tasks: (A1) Reliability > Novelty; (A2) Embed > Destination; (A3) Agency > Chat. We model adoption as a sum of a decaying novelty term…
We present a suite of reinforcement learning environments illustrating various safety properties of intelligent agents. These problems include safe interruptibility, avoiding side effects, absent supervisor, reward gaming, safe exploration,…
We introduce a unified mathematical and probabilistic framework for understanding and comparing diverse AI agent strategies. We bridge the gap between high-level agent design concepts, such as ReAct, multi-agent systems, and control flows,…
The A2AS framework is introduced as a security layer for AI agents and LLM-powered applications, similar to how HTTPS secures HTTP. A2AS enforces certified behavior, activates model self-defense, and ensures context window integrity. It…
We outline a vision for frontier AI auditing, which we define as rigorous third-party verification of frontier AI developers' safety and security claims, and evaluation of their systems and practices against relevant standards, based on…
This paper explores the intersection of quantum computing and agentic AI by examining how quantum technologies can enhance the capabilities of autonomous agents, and, conversely, how agentic AI can support the advancement of quantum…
Recent advancements in Web AI agents have demonstrated remarkable capabilities in addressing complex web navigation tasks. However, emerging research shows that these agents exhibit greater vulnerability compared to standalone Large…
Mobile agent technology offers a dramatically evolving computing paradigm in which a program, in the form of a software agent, can suspend its execution on a host computer, transfers itself to another agent-enabled host on the network, and…
Large Language Model (LLM) agents face security vulnerabilities spanning AI-specific and traditional software domains, yet current research addresses these separately. This study bridges this gap through comparative evaluation of Function…
Modern AI agents execute real-world side effects through tool calls such as file operations, shell commands, HTTP requests, and database queries. A single unsafe action, including accidental deletion, credential exposure, or data…
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI models drastically lower attack barriers, rendering current…
Agentic AI systems, built upon large language models (LLMs) and deployed in multi-agent configurations, are redefining intelligence, autonomy, collaboration, and decision-making across enterprise and societal domains. This review presents a…
Increased delegation of commercial, scientific, governmental, and personal activities to AI agents -- systems capable of pursuing complex goals with limited supervision -- may exacerbate existing societal risks and introduce new risks.…
Agentic AI represents a transformative shift in artificial intelligence, but its rapid advancement has led to a fragmented understanding, often conflating modern neural systems with outdated symbolic models -- a practice known as conceptual…
Verification and validation of agentic behavior have been suggested as important research priorities in efforts to reduce risks associated with the creation of general artificial intelligence (Russell et al 2015). In this paper we question…
As Large Language Model (LLM) agents become more capable, their coordinated use in the form of multi-agent systems is anticipated to emerge as a practical paradigm. Prior work has examined the safety and misuse risks associated with agents.…
The advent of large language models (LLMs) has catalyzed a transformative shift in artificial intelligence, paving the way for advanced intelligent agents capable of sophisticated reasoning, robust perception, and versatile action across…
European financial institutions face mounting regulatory pressure while their security operations centres remain constrained not by data or staffing but by reasoning capacity: enterprise SIEMs cover only a fraction of MITRE ATT&CK…
As Agentic AI systems evolve from basic workflows to complex multi agent collaboration, robust protocols such as Google's Agent2Agent (A2A) become essential enablers. To foster secure adoption and ensure the reliability of these complex…
Automated control monitors could play an important role in overseeing highly capable AI agents that we do not fully trust. Prior work has explored control monitoring in simplified settings, but scaling monitoring to real-world deployments…