Related papers: Parallax: Why AI Agents That Think Must Never Act
Recent reasoning-based safety guardrails for Large Reasoning Models (LRMs), such as deliberative alignment, have shown strong defense against jailbreak attacks. By leveraging LRMs' reasoning ability, these guardrails help the models to…
Real-world requests to AI agents are fundamentally underspecified. Natural human communication relies on shared context and unstated constraints that speakers expect listeners to infer. Current agentic benchmarks test explicit…
AI is moving from domain-specific autonomy in closed, predictable settings to large-language-model-driven agents that plan and act in open, cross-organizational environments. As a result, the cybersecurity risk landscape is changing in…
Agent frameworks increasingly encode tool-using behavior as explicit workflow graphs, yet safety enforcement remains a runtime concern. These frameworks expose analyzable graph structure through their APIs, enabling pre-deployment static…
AI agents have been boosted by large language models. AI agents can function as intelligent assistants and complete tasks on behalf of their users with access to tools and the ability to execute commands in their environments. Through…
Autonomous AI agents are being deployed with filesystem access, email control, and multi-step planning. This thesis contributes to four open problems in AI safety: understanding dangerous internal computations, removing dangerous behaviors…
The emergence of large language models has catalyzed two distinct yet interconnected paradigms in artificial intelligence: standalone AI Agents and collaborative Agentic AI ecosystems. This comprehensive study establishes a definitive…
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,…
Frontier AI Safety Policies concentrate on prevention: capability evaluations, deployment gates, and usage constraints, while neglecting the capacity to coordinate responses when prevention fails. We argue this coordination gap is…
Our computing ecosystem is being transformed by two emerging paradigms: the increased deployment of agentic AI systems and advancements in quantum computing. With respect to agentic AI systems, one of the most critical problems is creating…
AI policy guidance is predominantly written as prose, which practitioners must first convert into executable rules before frameworks can evaluate or enforce them. This manual step is slow, error-prone, difficult to scale, and often delays…
Security Operations Centers (SOCs) increasingly encounter difficulties in correlating heterogeneous alerts, interpreting multi-stage attack progressions, and selecting safe and effective response actions. This study introduces AgentSOC, a…
Agentic AI systems capable of reasoning, planning, and executing actions present fundamentally distinct governance challenges compared to traditional AI models. Unlike conventional AI, these systems exhibit emergent and unexpected behaviors…
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…
As autonomous AI agents increasingly mediate online platform markets, a fundamental question emerges: do these markets generate stable strategic outcomes? In repeated strategic environments, the Nash equilibrium provides a natural benchmark…
EVMbench, released by OpenAI, Paradigm, and OtterSec, is the first large-scale benchmark for AI agents on smart contract security. Its results -- agents detect up to 45.6% of vulnerabilities and exploit 72.2% of a curated subset -- have…
Autonomous Large Language Model (LLM) agents exhibit significant vulnerability to Indirect Prompt Injection (IPI) attacks. These attacks hijack agent behavior by polluting external information sources, exploiting fundamental trade-offs…
Recent advances in large language models (LLMs) have led to increasingly sophisticated safety protocols and features designed to prevent harmful, unethical, or unauthorized outputs. However, these guardrails remain susceptible to novel and…
As artificial intelligence scales, the concepts of alignment, agency, and autonomy have become central to AI safety, governance, and control. However, even in human contexts, these terms lack universal definitions, varying across…
Conventional algorithmic trading systems are grounded in deterministic heuristics or offline-trained statistical models that cannot adapt to the semantic complexity of rapidly shifting market regimes. This paper introduces AGENTICAITA, an…