Related papers: Before the Tool Call: Deterministic Pre-Action Aut…
As autonomous AI agents increasingly call other agents to complete tasks on behalf of a human principal, a structural accountability gap has emerged: the calling agent accepts the terms of service of the callee without any protocol-level…
As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…
Despite significant advancements in general-purpose AI agents, several challenges still hinder their practical application in real-world scenarios. First, the limited planning capabilities of Large Language Models (LLM) restrict AI agents…
Artificial intelligence now decides who receives a loan, who is flagged for criminal investigation, and whether an autonomous vehicle brakes in time. Governments have responded: the EU AI Act, the NIST Risk Management Framework, and the…
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:…
AI agents are now running real transactions, workflows, and sub-agent chains across organizational boundaries without continuous human supervision. This creates a problem no current infrastructure is equipped to solve: how do you identify,…
AI agents are autonomous entities that can be instantiated on demand, migrate across platforms, and interact with other agents or services without continuous human supervision. In such environments, identity is critical for establishing…
Large language models increasingly operate as autonomous agents that select and invoke tools from large registries. We identify a critical gap: when unauthorized tools are visible in an agent's context, models select them in adversarial…
Autonomous LLM agents can issue thousands of API calls per hour without human oversight. OAuth 2.0 assumes deterministic clients, but in agentic settings stochastic reasoning, prompt injection, or multi-agent orchestration can silently…
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…
Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it deletes unrelated files, wipes a stale credentials backup, or rewrites…
Current AI systems increasingly operate in contexts where their outputs directly trigger real-world actions. Most existing approaches to AI safety, risk management, and governance focus on post-hoc validation, probabilistic risk estimation,…
An auditor instructs an AI assistant: "open each file individually using the Read tool -- no scripts, no agents." The AI replies "Yes" -- then issues a single batched call summarizing all fifty files at once. We call this the Compliance…
We formalize trust calibration for agentic tool use (deciding when an automated agent's proposed action may execute autonomously versus require human approval) as a preference-learning problem. A policy gateway maintains a Gaussian-process…
The downstream use cases, benefits, and risks of AI models depend significantly on what sort of access is provided to the model, and who it is provided to. Though existing safety frameworks and AI developer usage policies recognise that the…
AI agents interact with external environments through tool calls, exposing them to attacks like indirect prompt injection that can trigger unauthorized actions. Securing these agents is challenging: they behave autonomously and…
Existing AI agent safety benchmarks focus on generic criminal harm (cybercrime, harassment, weapon synthesis), leaving a systematic blind spot for a distinct and commercially consequential threat category: agents harming their own…
Recent advances have enabled LLM-powered AI agents to autonomously execute complex tasks by combining language model reasoning with tools, memory, and web access. But can these systems be trusted to follow deployment policies in realistic…
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…
As AI agents increasingly perform economic tasks on behalf of humans, a fundamental tension arises between agent autonomy and human control over financial assets. We present the Agent Economic Sovereignty Protocol (AESP), a layered protocol…