Related papers: AgentLAB: Benchmarking LLM Agents against Long-Hor…
Compared to traditional models, agentic AI represents a highly valuable target for potential attackers as they possess privileged access to data sources and API tools, which are traditionally not incorporated into classical agents. Unlike a…
Despite the rapid advancement of LLM-based agents, the reliable evaluation of their safety and security remains a significant challenge. Existing rule-based or LLM-based evaluators often miss dangers in agents' step-by-step actions,…
Large Language Model (LLM) agents exhibit remarkable performance across diverse applications by using external tools to interact with environments. However, integrating external tools introduces security risks, such as indirect prompt…
The strong planning and reasoning capabilities of Large Language Models (LLMs) have fostered the development of agent-based systems capable of leveraging external tools and interacting with increasingly complex environments. However, these…
As LLM-driven agents advance in cybersecurity, Jeopardy CTF benchmarks are approaching saturation and cyber ranges, the natural next evaluation frontier, offer diminishing resistance under their current static design. We validate this…
Memory is a central capability for LLM agents operating across long-horizon tasks. Existing memory benchmarks predominantly evaluate retention of personalized information in multi-turn chat scenarios, overlooking the dynamic memory…
The emergence of Large Language Models (LLMs) has reshaped agent systems. Unlike traditional rule-based agents with limited task scope, LLM-powered agents offer greater flexibility, cross-domain reasoning, and natural language interaction.…
LLM-based agent systems are emerging as a new software paradigm and have been widely adopted across diverse domains such as medicine, robotics, and programming. However, maintaining these systems requires substantial effort, as they are…
Recent advances in large vision-language models (VLMs) have demonstrated generalizable open-vocabulary perception and reasoning, yet their real-robot manipulation capability remains unclear for long-horizon, closed-loop execution in…
With ChatGPT-like large language models (LLM) prevailing in the community, how to evaluate the ability of LLMs is an open question. Existing evaluation methods suffer from following shortcomings: (1) constrained evaluation abilities, (2)…
Large Vision-Language Models (LVLMs) empower autonomous mobile agents, yet their security under realistic mobile deployment constraints remains underexplored. While agents are vulnerable to visual prompt injections, stealthily executing…
With the rapid advancement of Large Language Models (LLMs), significant progress has been made in multi-agent applications. However, the complexities in coordinating agents' cooperation and LLMs' erratic performance pose notable challenges…
Personal AI agents like OpenClaw run with elevated privileges on users' local machines, where a single successful prompt injection can leak credentials, redirect financial transactions, or destroy files. This threat goes well beyond…
LLM-based agents are becoming increasingly capable, yet their safety lags behind. This creates a gap between what agents can do and should do. This gap widens as agents engage in multi-turn interactions and employ diverse tools, introducing…
Large Language Model (LLM) agents are powering a growing share of interactive web applications, yet remain vulnerable to misuse and harm. Prior jailbreak research has largely focused on single-turn prompts, whereas real harassment often…
The rapid advancement of large language model (LLM) agents has raised new concerns regarding their safety and security. In this paper, we propose GuardAgent, the first guardrail agent to protect target agents by dynamically checking whether…
Securing AI agents powered by Large Language Models (LLMs) represents one of the most critical challenges in AI security today. Unlike traditional software, AI agents leverage LLMs as their "brain" to autonomously perform actions via…
LLM agents increasingly perform end-to-end ML engineering tasks where success is judged by a single scalar test metric. This creates a structural vulnerability: an agent can increase the reported score by compromising the evaluation…
With the rapid development of multimodal large language models (MLLMs), they are increasingly deployed as autonomous computer-use agents capable of accomplishing complex computer tasks. However, a pressing issue arises: Can the safety risk…
Agentic AI systems powered by large language models (LLMs) and endowed with planning, tool use, memory, and autonomy, are emerging as powerful, flexible platforms for automation. Their ability to autonomously execute tasks across web,…