Related papers: SafetyDrift: Predicting When AI Agents Cross the L…

The rise of AI agent frameworks has introduced agent skills, modular packages containing instructions and executable code that dynamically extend agent capabilities. While this architecture enables powerful customization, skills execute…

LLM-based multi-agent systems are increasingly deployed on long-horizon tasks, but a single decisive error is often accepted by downstream agents and cascades into trajectory-level failure. Existing work frames this as \emph{post-hoc…

Large language models are increasingly deployed as *deep agents* that plan, maintain persistent state, and invoke external tools, shifting safety failures from unsafe text to unsafe *trajectories*. We introduce **AgentFence**, an…

User models in information retrieval rest on a foundational assumption that observed behavior reveals intent. This assumption collapses when the user is an AI agent privately configured by a human operator. For any action an agent takes, a…

In recent years, Large-Language-Model-driven AI agents have exhibited unprecedented intelligence and adaptability. Nowadays, agents are undergoing a new round of evolution. They no longer act as an isolated island like LLMs. Instead, they…

Information Retrieval is shifting from passive document ranking toward autonomous agentic workflows that operate in multi-step Reason-Act-Observe loops. In such long-horizon trajectories, minor early errors can cascade, leading to…

Code-capable large language model (LLM) agents are increasingly embedded into software engineering workflows where they can read, write, and execute code, raising the stakes of safety-bypass ("jailbreak") attacks beyond text-only settings.…

Background. Traditional safety benchmarks for language models evaluate generated text: whether a model outputs toxic language, reproduces bias, or follows harmful instructions. When models are deployed as agents, the safety-relevant object…

Humans are capable of strategically deceptive behavior: behaving helpfully in most situations, but then behaving very differently in order to pursue alternative objectives when given the opportunity. If an AI system learned such a deceptive…

Multi-agent Large Language Model (LLM) systems create privacy risks that current benchmarks cannot measure. When agents coordinate on tasks, sensitive data passes through inter-agent messages, shared memory, and tool arguments, all pathways…

LLM agents do not act on raw interaction history; they act on a bounded decision state assembled by truncation, summarization, reordering, and rewriting. If directive-bearing state is dropped, weakened, or rebound during that step, an agent…

Large Language Models (LLMs) are increasingly integrated into vehicle-based digital assistants, where unsafe, ambiguous, or legally incorrect responses can lead to serious safety, ethical, and regulatory consequences. Despite growing…

LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that evolves its strategies over hundreds of rounds and tested it against nine defense…

Multi-agent AI pipelines typically assume that agent misconduct originates from model misalignment. We identify a structural failure in this assumption, the \emph{Misattribution Gap}, where memory-layer attacks produce behaviors…

As autonomous driving technology matures, safety and robustness of its key components, including trajectory prediction, is vital. Though real-world datasets, such as Waymo Open Motion, provide realistic recorded scenarios for model…

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…

A multimodal large language model (MLLM) agent can receive instructions, capture images, retrieve histories from memory, and decide which tools to use. Nonetheless, red-teaming efforts have revealed that adversarial images/prompts can…

Large language models (LLMs) are shown to be vulnerable to jailbreaking attacks where adversarial prompts are designed to elicit harmful responses. While existing defenses effectively mitigate single-turn attacks by detecting and filtering…

As autonomous agents (e.g., OpenClaw) increasingly operate with deep system-level privileges to execute complex tasks, they introduce severe, unmitigated security risks. Current vulnerability analyses overwhelmingly focus on single-turn,…

Vulnerability of Frontier language models to misuse and jailbreaks has prompted the development of safety measures like filters and alignment training in an effort to ensure safety through robustness to adversarially crafted prompts. We…