Related papers: Sovereign Agentic Loops: Decoupling AI Reasoning f…
Tool-augmented LLM systems expose a control regime that learning theory has largely ignored: sequential decision-making with a massive discrete action universe (tools, APIs, documents) in which only a small, unknown subset is relevant for…
As AI agents increasingly operate in complex environments, ensuring reliable, context-aware privacy is critical for regulatory compliance. Traditional access controls are insufficient because privacy risks often arise after access is…
Agentic AI systems, possessing capabilities for autonomous planning and action, show great potential across diverse domains. However, their practical deployment is hindered by challenges in aligning their behavior with varied human values,…
Recent advances in agentic AI have shifted the focus from standalone Large Language Models (LLMs) to integrated systems that combine LLMs with tools, memory, and other agents to perform complex tasks. These multi-agent architectures enable…
Recent advancements on Large Language Models (LLMs) enable AI Agents to automatically generate and execute multi-step plans to solve complex tasks. However, since LLM's content generation process is hardly controllable, current LLM-based…
The recent development of Large Language Models (LLMs) enables the rise of App agents that interpret user intent and operate smartphone Apps through actions such as clicking and scrolling. While prompt-based solutions with proprietary LLM…
What does it mean to plan? Current agentic systems, whether scaffolded workflows or end-to-end policies, rely on reactive decision-making: selecting the next action via a fixed procedure with at most undifferentiated adaptive computation…
The proliferation of Large Language Models (LLMs) has opened new frontiers in computing, yet controlling and orchestrating their capabilities beyond simple text generation remains a challenge. Current methods, such as function/tool calling…
Large language model (LLM) agents face a structural tension: cloud agents provide strong reasoning but expose user data, while on-device agents preserve privacy at the cost of overall capability. Existing device-cloud designs treat this…
LLM-based agentic systems are rapidly evolving to perform complex autonomous tasks through dynamic tool invocation, stateful memory management, and multi-agent collaboration. However, this semantics-driven execution paradigm creates a…
Agent Skill framework, now widely and officially supported by major players such as GitHub Copilot, LangChain, and OpenAI, performs especially well with proprietary models by improving context engineering, reducing hallucinations, and…
Large language models can consult information that fixed static analyzers cannot, such as documentation, current security advisories, version-specific metadata, and informal API contracts. This makes LLMs a compelling option for program…
Multi-agent systems extend large language models (LLMs) by decomposing tasks among specialized agents, but their distributed decision process creates new attack surfaces. We identify semantic hijacking, an attack in which harmful requests…
Current agentic AI architectures are fundamentally incompatible with the security and epistemological requirements of high-stakes scientific workflows. The problem is not inadequate alignment or insufficient guardrails, it is architectural:…
The temporal assumptions underpinning conventional Identity and Access Management collapse under agentic execution regimes. A sixty-second revocation window permits on the order of $6 \times 10^3$ unauthorized API calls at 100 ops/tick; at…
Research on large language model (LLM) security is shifting from "will the model leak training data" to a more consequential question: can an agent with persistent, long-term memory be continuously shaped, cross-session poisoned, accessed…
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…
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…
Large language models (LLM) are perceived to offer promising potentials for automating security tasks, such as those found in security operation centers (SOCs). As a first step towards evaluating this perceived potential, we investigate the…
Modern AI agents routinely depend on secrets such as API keys and SSH credentials, yet the dominant deployment model still exposes those secrets directly to the agent process through environment variables, local files, or forwarding…