44 articles mentioning computer-10
arXiv:2610.27954v1 Announce Type: new Abstract: Recent advances in large (vision) language models have enabled computer-use agents that automate digital workflows via fine-grained keyboard and mouse operations. However, such agents remain fragile in long-horizon settings, where errors accumulate and
arXiv:2610.27645v1 Announce Type: new Abstract: As computer-use agents (CUAs) move to long-horizon workflows spanning multiple applications, undetected errors can silently corrupt persistent state and cause cascading failures in subsequent actions. Reliable error detection and recovery have become c
arXiv:2610.22990v1 Announce Type: cross Abstract: Computer-use agents (CUAs) are commonly evaluated against fixed task specifications, but users may omit requirements, add constraints, or require approval before consequential actions. Completing the benchmark instruction does not guarantee serving t
arXiv:2610.23012v1 Announce Type: new Abstract: Recent advances in multimodal foundation models have significantly improved the ability to operate real-world software through graphical user interfaces (GUIs) using visual observations and natural language instructions. However, maintaining strong per
arXiv:2610.22234v1 Announce Type: cross Abstract: Real desktop automation is neither purely visual nor purely programmatic. Agents must understand user-facing interfaces while efficiently manipulating files, scripts, and system state. However, native GUI/code coordination cannot be obtained by promp
arXiv:2610.20939v1 Announce Type: new Abstract: Online reinforcement learning (RL) with verifiable rewards has driven rapid progress in mathematics, coding, and tool use, but scaling this success to GUI agents remains challenging due to the high cost of interactive environments and the scarcity of r
arXiv:2610.22280v1 Announce Type: new Abstract: Computer-use agents increasingly tackle long-horizon tasks, where running a frontier model at every step is expensive and a small open-weight model alone often fails. Weak-to-strong escalation offers a middle ground where a weak agent acts by default a
arXiv:2610.19347v1 Announce Type: new Abstract: Novelty detection is crucial in various technological and scientific domains. Its importance spans from ensuring the reliability of sensor networks to enhancing the adaptability of computer vision systems. As AI systems become increasingly sophisticate
arXiv:2610.17410v1 Announce Type: new Abstract: Advances in large-scale machine learning have enabled agentic AI systems: persistent, autonomous computational entities that pursue goals, initiate actions, and interact with open environments. These systems are often framed as applications of foundati
arXiv:2606.15034v3 Announce Type: replace Abstract: Computer-use agents can complete benign user instructions while violating important constraints of the user's environment. We introduce OSGuard, a dual-granularity benchmark suite for evaluating safety through local, pre-execution guardrail decisio
arXiv:2610.11050v1 Announce Type: new Abstract: Computer-use agents are capable of completing complex tasks, increasing the use of automatic judges to determine success, either for training or for evaluation without human involvement. Despite their flexibility, their reliability on long tasks spanni
Learn how OpenAI and Ironclad are training and evaluating AI agents on complex contracting workflows to advance computer use for professional work.
arXiv:2610.02320v1 Announce Type: cross Abstract: Computer-use agents need to reliably ground action targets in complex desktop scenes, where multiple applications, overlapping windows, and visually similar controls compete for attention. Existing training data rarely pair such scenes with dense ann
arXiv:2610.03089v1 Announce Type: cross Abstract: Modern Computer Use Agents (CUAs) directly interact with graphical user interfaces and execute third-party web tools, exposing them to indirect prompt injection across every rendered page and tool response. While the Dual-LLM pattern is the primary s
arXiv:2602.03255v2 Announce Type: replace Abstract: Computer-use agents (CUAs) execute multi-stage tasks through tools, where an early unsafe decision can propagate to consequential actions. Evaluating only final outcomes can miss such decisions, while constructing executable environments for new ta
arXiv:2610.03537v1 Announce Type: cross Abstract: Endovascular brain-computer interfaces (BCIs) avoid craniotomy but require precise device delivery through anatomically variable cerebral veins. This work presents the first demonstration of in vitro autonomous robotic navigation for endovascular BCI
arXiv:2610.02932v1 Announce Type: new Abstract: Compiling GUI procedures that agents execute repeatedly into programs can reduce their token costs. However, measuring payback and deciding when to compile have two challenges. First, compilation costs are uncertain because attempts can require repair
arXiv:2606.00341v2 Announce Type: replace Abstract: As AI agents are increasingly deployed in real personal and corporate settings (email accounts, development workflows, company databases, etc.), safety considerations surrounding these agents become paramount. Although much work has focused on agen
arXiv:2610.00666v1 Announce Type: cross Abstract: Qualitative comparison figures are central evidence in computer vision papers, and vision-language models (VLMs) are increasingly used to judge them. Yet existing benchmarks score only scalar quality or overall preference, so a judge can be rewarded
arXiv:2609.40284v1 Announce Type: cross Abstract: Computer use agents (CUAs), which use graphical user interfaces (GUIs) to complete tasks on a computer, have recently surpassed human performance on many standard benchmarks, including difficult long-horizon tasks. Their capabilities are undoubtedly
arXiv:2605.14698v2 Announce Type: replace Abstract: Foundation models (FMs) promise to extract unified representations that generalize across downstream tasks. They have emerged across fields, including electroencephalography (EEG), but it is less clear how effective they are in this particular fiel
arXiv:2609.40253v2 Announce Type: replace-cross Abstract: Online training enables computer-use agents (CUAs) to improve through interaction with executable environments. However, existing methods primarily rely on sparse outcome rewards, which provide no supervision for intermediate actions. On-poli
arXiv:2606.25760v2 Announce Type: replace-cross Abstract: Computer-use agents turn vision-language model (VLM) predictions into executable GUI clicks, so reliable uncertainty estimates are essential for rejection, calibration, miss-severity ranking, and spatial safety regions. Yet evidence on post-h
arXiv:2609.39903v1 Announce Type: new Abstract: Scientific software presents a demanding test for computer-using agents based on visual language models (VLMs): completing a research workflow requires interpreting specialized interfaces, manipulating scientific objects, and producing verifiable resul
arXiv:2609.37176v1 Announce Type: new Abstract: Computer-use agents have become increasingly capable of executing tasks on live desktops through natural-language instructions, based on trajectories of screenshots, actions, and reasoning. We discover that they can stealthily exhibit inertia, in which
arXiv:2609.36201v1 Announce Type: cross Abstract: Computer-use agents (CUAs), while capable of completing computer tasks in everyday and professional workflows, can cause unintended harm even under benign instructions and environments. However, detecting such harm remains challenging. First, it requ
arXiv:2609.36736v1 Announce Type: cross Abstract: Speech brain-computer interfaces (BCIs) aim to restore communication by transforming neural activity related to speech, language, or communicative intent into external outputs such as text, synthesized voice, or avatar control. Recent advances in int
arXiv:2609.36927v1 Announce Type: new Abstract: Many computer tasks recur: the same workflow runs many times, with new inputs and from different starting states. Current computer-use agents re-plan every step of every run, which makes them costly and unreliable on such tasks. We introduce neuro-symb
arXiv:2609.17885v2 Announce Type: replace Abstract: Computer-use agents that operate through screenshots and simulated actions are advancing rapidly, yet their evaluation remains anchored to general desktop and web tasks. Enterprise Resource Planning systems run the finance, procurement, inventory,
arXiv:2609.16251v2 Announce Type: replace Abstract: Computer-use agents are increasingly evaluated in realistic desktop environments, but existing benchmarks provide limited coverage of professional engineering workflows whose outputs are persistent, structured artifacts. Mechanical computer-aided d
arXiv:2605.12481v2 Announce Type: replace Abstract: Computer Use Agents (CUAs) can act through both atomic GUI actions, such as click and type, and high-level tool calls, such as API-based file operations, but this hybrid action space often leaves them uncertain about when to continue with GUI actio
arXiv:2609.22178v2 Announce Type: cross Abstract: Computer-use agents (CUAs) have made rapid progress in completing complex tasks through graphical user interfaces, yet post-training centered on task success alone does not induce reliable safety behavior. A reliable CUA must condition its execution
arXiv:2609.24890v1 Announce Type: cross Abstract: Evaluation of Computer-Use Agents (CUAs) is often limited to the final deliverables they create (at the end of hundreds of steps) and assessed with functional verifiers, as seen in OSWorld. However, such evaluation of end-state performance lacks tran
arXiv:2609.22207v1 Announce Type: cross Abstract: High-rate neural telemetry requires an implant-towearable link whose circuit partition, waveform mapping, packet processing, and failure semantics are mutually consistent. This paper specifies a chip-oriented, one-way impulse-radio ultrawideband (IR-
arXiv:2609.24249v1 Announce Type: new Abstract: Neural networks, both convolution or transformer based, are essential for modern computer vision systems. However, they are vulnerable to small perturbations, almost imperceptible to humans, which significantly alter the model's prediction. These adver
arXiv:2609.20904v1 Announce Type: cross Abstract: Hybrid motor-imagery brain-computer interfaces (MI-BCIs) combining EEG and fNIRS can outperform EEG-only systems by exploiting complementary electrophysiological and hemodynamic information. To obtain such hybrid information when paired EEG-fNIRS acq
arXiv:2609.22088v1 Announce Type: cross Abstract: Brain-computer interfaces (BCIs) decode neural activity into commands, yet most existing systems rely on fixed-window decoding that may result in redundant observation or unreliable predictions due to insufficient evidence. Adaptive temporal decision
arXiv:2609.22000v2 Announce Type: replace Abstract: Computer-use agents (CUAs) have advanced along two separate lines: graphical interaction and software development through code and the command line. Real digital work requires both, interleaved rather than stacked end to end. We study hybrid CUAs t
Muse is now available on the Mac, where it can work with your files and apps to take action on your behalf.
arXiv:2609.19387v1 Announce Type: new Abstract: Agents are increasingly asked to design hardware, and increasingly reported to succeed. Such reports establish that a design improved; they cannot establish why. An agent that improves an accelerator may be reasoning about the machine, or may be search
arXiv:2602.17772v3 Announce Type: replace-cross Abstract: Electroencephalography (EEG)-based P300 brain-computer interfaces (BCIs) enable communication without physical movement by detecting stimulus-evoked neural responses. Accurate and efficient decoding remains challenging due to high dimensional
arXiv:2510.09653v4 Announce Type: replace-cross Abstract: This paper presents a comprehensive overview of the Ultralytics YOLO family, emphasizing architectural evolution, benchmarking, deployment, and emerging directions from YOLOv5 through YOLO27. The review begins with YOLO27 (or YOLOv27), which
arXiv:2609.16157v1 Announce Type: cross Abstract: Numerical simulations reveal how vortices stretch and transfer energy, but establishing smooth evolution requires bounds that remain valid beyond the simulated resolution. Here I develop a computer-assisted framework that establishes global regularit
arXiv:2608.26204v2 Announce Type: replace-cross Abstract: Computer Use Agents (CUAs) are increasingly deployed to navigate mobile and desktop applications on behalf of users, yet no benchmark comprehensively evaluates whether they can safely interact with visual interfaces while handling ambiguous i