Related papers: Benchmarking Autonomous Agents against Temporal, S…

As Large Language Models (LLMs) evolve into autonomous agents, existing safety evaluations face a fundamental trade-off: manual benchmarks are costly, while LLM-based simulators are scalable but suffer from logic hallucination. We present…

The widespread deployment of LLM-based agents is likely to introduce a critical privacy threat: malicious agents that proactively engage others in multi-turn interactions to extract sensitive information. However, the evolving nature of…

Large language model (LLM)-based agents combine LLMs with external tools to automate tasks such as scheduling meetings, managing documents, or booking travel. While these integrations unlock powerful capabilities, they also create new and…

Modern agentic frameworks (e.g., CrewAI and AutoGen) have evolved into complex, autonomous multi-agent systems, introducing unique reliability challenges beyond earlier pipeline-based LLM libraries. However, existing empirical studies focus…

The growing adoption of large language models (LLMs) has led to a new paradigm in mobile computing--LLM-powered mobile AI agents--capable of decomposing and automating complex tasks directly on smartphones. However, the security…

Ensuring the safety and reliability of large language models (LLMs) in clinical practice is critical to prevent patient harm. However, LLMs are advancing so rapidly that static benchmarks quickly become obsolete or prone to overfitting,…

As large language models (LLMs) evolve from conversational assistants into autonomous agents, evaluating the safety of their actions becomes critical. Prior safety benchmarks have primarily focused on preventing generation of harmful…

Large language model (LLM) agents have demonstrated remarkable capabilities in complex reasoning and decision-making by leveraging external tools. However, this tool-centric paradigm introduces a previously underexplored attack surface,…

We identify and formalize a novel security risk: Context-Fragmented Violations (CFVs) - a class of policy breaches where individual agent actions appear locally safe and reasonable, yet collectively violate organizational policies because…

Semantic caching has emerged as a pivotal technique for scaling LLM applications, widely adopted by major providers including AWS and Microsoft. By utilizing semantic embedding vectors as cache keys, this mechanism effectively minimizes…

Autonomous vehicles (AVs) rely on complex perception and communication systems, making them vulnerable to adversarial attacks that can compromise safety. While simulation offers a scalable and safe environment for robustness testing,…

Large Language Models (LLMs) are rapidly transitioning from conversational assistants to autonomous agents embedded in critical organizational functions, including Security Operations Centers (SOCs), financial systems, and infrastructure…

LLM-based agents represent a paradigm shift in AI, enabling autonomous systems to plan, reason, and use tools while interacting with dynamic environments. This paper provides the first comprehensive survey of evaluation methods for these…

Large language model-based multi-agent systems have shown great abilities across various tasks due to the collaboration of expert agents, each focusing on a specific domain. However, the impact of clumsy or even malicious agents--those who…

Language agents powered by large language models (LLMs) have seen exploding development. Their capability of using language as a vehicle for thought and communication lends an incredible level of flexibility and versatility. People have…

Large Language Model (LLM) agents, which integrate planning, memory, reflection, and tool-use modules, have shown promise in solving complex, multi-step tasks. Yet their sophisticated architectures amplify vulnerability to cascading…

The proliferation of autonomous AI agents marks a paradigm shift toward complex, emergent multi-agent systems. This transition introduces systemic security risks, including control-flow hijacking and cascading failures, that traditional…

We introduce the Cyber Defense Benchmark, a benchmark for measuring how well large language model (LLM) agents perform the core SOC analyst task of threat hunting: given a database of raw Windows event logs with no guided questions or…

Large Language Models (LLMs) guardrail systems are designed to protect against prompt injection and jailbreak attacks. However, they remain vulnerable to evasion techniques. We demonstrate two approaches for bypassing LLM prompt injection…

Autonomous AI agents deployed on platforms such as OpenClaw face prompt injection, memory poisoning, supply-chain attacks, and social engineering, yet existing defences address only the platform perimeter, leaving the agent's own threat…