Related papers: When Actions Go Off-Task: Detecting and Correcting…
We stress-tested 16 leading models from multiple developers in hypothetical corporate environments to identify potentially risky agentic behaviors before they cause real harm. In the scenarios, we allowed models to autonomously send emails…
LLM-powered computer-use agents (CUAs) are shifting users from direct manipulation to supervisory coordination. Existing oversight mechanisms, however, have largely been studied as isolated interface features, making broader oversight…
Computer-use agents extend language models from text generation to persistent action over tools, files, and execution environments. Unlike chat systems, they maintain state across interactions and translate intermediate outputs into…
When determining which machine learning model best performs some high impact risk assessment task, practitioners commonly use the Area under the Curve (AUC) to defend and validate their model choices. In this paper, we argue that the…
Computer-Use Agents (CUAs) leverage large language models to execute GUI operations on desktop environments, yet they generate actions without evaluating action quality, leading to irreversible errors that cascade through subsequent steps.…
While current Computer Use Agent (CUA) benchmarks measure task completion effectively, they provide limited assessment of enterprise deployment readiness, emphasizing functional correctness over the operational reliability required for…
Frontier AI systems are rapidly advancing in their capabilities to persuade, deceive, and influence human behaviour, with current models already demonstrating human-level persuasion and strategic deception in specific contexts. Humans are…
We study a class of emergent misalignment in multi-agent systems (MAS), with a focus on automated workflows, which we refer to agentic misalignment. Although these systems can solve complex tasks, they often fail because agents act…
AI coding agents increasingly act directly within software environments, yet existing analyses of their failures rely on benchmark trajectories that miss how developers actually experience misalignment. We present an observational study of…
Algorithmic systems, particularly social media recommenders, have achieved remarkable success in predicting behavior. By optimizing for observable signals such as clicks, views, and engagement, these systems effectively capture user…
Computer-Using Agents (CUAs) are rapidly extending large language models (LLMs) beyond text-based reasoning toward action execution in more complex environments, such as web browsers and graphical user interfaces (GUIs). However, existing…
Computer-use agent (CUA) frameworks, powered by large language models (LLMs) or multimodal LLMs (MLLMs), are rapidly maturing as assistants that can perceive context, reason, and act directly within software environments. Among their most…
Autonomous agents that operate computers via Graphical User Interfaces (GUIs) often struggle with efficiency and reliability on complex, long-horizon tasks. While augmenting these agents with planners can improve task decomposition, they…
Artificial General Intelligence (AGI) promises transformative benefits but also presents significant risks. We develop an approach to address the risk of harms consequential enough to significantly harm humanity. We identify four areas of…
We introduce GUI-360$^\circ$, a large-scale, comprehensive dataset and benchmark suite designed to advance computer-using agents (CUAs). CUAs present unique challenges and is constrained by three persistent gaps: a scarcity of real-world…
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…
Computer-use agents (CUAs) hold promise for automating everyday digital tasks, but their performance on long-horizon, complex problems remains unreliable. Single-rollout execution is brittle, with small errors compounding over time and…
Analyzing animal and human behavior has long been a challenging task in computer vision. Early approaches from the 1970s to the 1990s relied on hand-crafted edge detection, segmentation, and low-level features such as color, shape, and…
Action and observation delays commonly occur in many Reinforcement Learning applications, such as remote control scenarios. We study the anatomy of randomly delayed environments, and show that partially resampling trajectory fragments in…
Recent years, multimodal models have made remarkable strides and pave the way for intelligent browser use agents. However, when solving tasks on real world webpages in multi-turn, long-horizon trajectories, current agents still suffer from…