Related papers: An Agentic Multi-Agent Architecture for Cybersecur…
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…
Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…
Cybersecurity is being fundamentally reshaped by foundation-model-based artificial intelligence. Large language models now enable autonomous planning, tool orchestration, and strategic adaptation at scale, challenging security architectures…
This paper introduces a multi-agent framework guided by Large Language Models (LLMs) to assist in the early stages of engineering design, a phase often characterized by vast parameter spaces and inherent uncertainty. Operating under a…
Automated intrusion-style workflows require LLM agents to reason over partial observations, tool outputs, and executable artifacts under bounded budgets. A single LLM instance often compresses evidence extraction, planning, execution, and…
AI agents have been developed for complex real-world tasks from coding to customer service. But AI agent evaluations suffer from many challenges that undermine our understanding of how well agents really work. We introduce the Holistic…
Enterprises are rapidly deploying large language models, retrieval augmented generation pipelines, and tool using agents into production, often on shared high performance computing clusters and cloud accelerator platforms that also support…
Collaborative agentic AI is projected to transform entire industries by enabling AI-powered agents to autonomously perceive, plan, and act within digital environments. Yet, current solutions in this field are all built in isolation, and we…
Security operations centers (SOCs) face a persistent challenge: efficiently triaging a high volume of user-reported phishing emails while maintaining robust protection against threats. This paper presents the first randomized controlled…
We investigate the Free Energy Principle as a foundation for measuring risk in agentic and multi-agent systems. From these principles we introduce a Cumulative Risk Exposure metric that is flexible to differing contexts and needs. We…
Computer-use agents provide a promising path toward general software automation because they can interact directly with arbitrary graphical user interfaces instead of relying on brittle, application-specific integrations. Despite recent…
Agentic language models operate in a fundamentally different safety regime than chat models: they must plan, call tools, and execute long-horizon actions where a single misstep, such as accessing files or entering credentials, can cause…
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…
The increasing integration of AI agents into cyber-physical systems (CPS) introduces new security risks that extend beyond traditional cyber or physical threat models. Recent advances in generative AI enable deepfake and semantic…
AI agent systems increasingly rely on reusable non-LLM engineering infrastructure that packages tool mediation, context handling, delegation, safety control, and orchestration. Yet the architectural design decisions in this surrounding…
Software testing has progressed toward intelligent automation, yet current AI-based test generators still suffer from static, single-shot outputs that frequently produce invalid, redundant, or non-executable tests due to the lack of…
The rapid proliferation of large language models (LLMs) has intensified the requirement for reliable safety evaluation to uncover model vulnerabilities. To this end, numerous LLM safety evaluation benchmarks are proposed. However, existing…
The deployment of AI models in clinical practice faces a critical challenge: models achieving expert-level performance on benchmarks can fail catastrophically when confronted with real-world variations in medical imaging. Minor shifts in…
Large language models hold considerable promise for various applications, but their computational requirements create a barrier that many institutions cannot overcome. A single session using a 70-billion-parameter model can cost around $127…
Web agents automate browser tasks, ranging from simple form completion to complex workflows like ordering groceries. While current benchmarks evaluate general-purpose performance~(e.g., WebArena) or safety against malicious actions~(e.g.,…