Related papers: Atomicity for Agents: Exposing, Exploiting, and Mi…
Large Language Models (LLMs) have demonstrated strong capabilities as autonomous agents through tool use, planning, and decision-making abilities, leading to their widespread adoption across diverse tasks. As task complexity grows,…
Computer-use agents (CUAs) that interact with real computer systems can perform automated tasks but face critical safety risks. Ambiguous instructions may trigger harmful actions, and adversarial users can manipulate tool execution to…
Large language model (LLM) agents are increasingly used to interact with and execute tasks in dynamic environments. However, a critical yet overlooked limitation of these agents is that they, by default, assume a stationary context, failing…
Multi-agent systems achieve state-of-the-art outcomes through peer collaboration. However, when an agent in the pipeline silently drops a constraint, the system's final output may look correct even though the reasoning chain was quietly…
AI-powered web agents have the potential to automate repetitive tasks, such as form filling, information retrieval, and scheduling, but they struggle to reliably execute these tasks without human intervention, requiring users to provide…
Threat emulators are tools or sets of scripts that emulate cyber attacks or malicious behavior. They can be used to create and launch single procedure attacks and multi-step attacks; the resulting attacks may be known or unknown cyber…
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,…
LLM-based agents are becoming increasingly proficient at solving web-based tasks. With this capability comes a greater risk of misuse for malicious purposes, such as posting misinformation in an online forum or selling illicit substances on…
In recent years, agentic artificial intelligence (AI) systems are becoming increasingly widespread. These systems allow agents to use various tools, such as web browsers, compilers, and more. However, despite their popularity, agentic AI…
Recent advancements in large language models (LLMs) have empowered autonomous web agents to execute natural language instructions directly on real-world webpages. However, existing agents often struggle with complex tasks involving dynamic…
Real-world agentic tasks, unlike synchronous Markov Decision Processes (MDPs), often involve non-blocking actions with variable latencies, creating a fundamental \textit{Temporal Gap} between action initiation and completion. Existing…
Autonomous agents operating within real-world environments often rely on automated planners to ascertain optimal actions towards desired goals or the optimization of a specified objective function. Integral to these agents are common…
Existing web agent benchmarks have largely converged on short, single-site tasks that frontier models are approaching saturation on. However, real world web use consists of long-horizon, multi-site workflows. Common web navigation tasks,…
In the event that a bacteriological or chemical toxin is intro- duced to a water distribution network, a large population of consumers may become exposed to the contaminant. A contamination event may be poorly predictable dynamic process…
Accessibility checkers are tools in support of accessible app development, and their use is encouraged by accessibility best practices. However, most current checkers evaluate static or mechanically-generated contexts, failing to capture…
Building Graphical User Interface (GUI) agents is a promising research direction, which simulates human interaction with computers or mobile phones to perform diverse GUI tasks. However, a major challenge in developing generalized GUI…
As autonomous AI agents increasingly populate the Internet, a novel security challenge arises: "Is this entity an AI agent?" It is a new entity-type verification problem with no established solution. We formalize the problem through a…
In late 2017, a sudden proliferation of malicious JavaScript was reported on the Web: browser-based mining exploited the CPU time of website visitors to mine the cryptocurrency Monero. Several studies measured the deployment of such code…
General virtual agents need to handle multimodal observations, master complex action spaces, and self-improve in dynamic, open-domain environments. However, existing environments are often domain-specific and require complex setups, which…
Despite advances in multimodal large language models, autonomous web agents still struggle to reliably execute long-horizon tasks on complex and dynamic web interfaces. Existing agents often suffer from inaccurate element grounding, the…