Related papers: TClone: Low-Latency Forking of Live GUI Environmen…
Computer-Use Agents (CUAs) are emerging as a new paradigm in human-computer interaction, enabling autonomous execution of tasks in desktop environment by perceiving high-level natural-language instructions. As such agents become…
CLI agents are the closest thing language models have to an embodied setting: the model emits commands, the terminal executes them, and the returned stream -- stdout, errors, files, logs, and traces -- records the consequences. We argue…
Recent advances in agentic AI have enabled increasingly autonomous workflows, but existing systems still face substantial challenges in achieving reliable deployment in real-world scientific research. In this work, we present a safe,…
Training computer use agents requires full-featured OS sandboxes with GUI environments, which consume substantial hardware resources as the number of sandboxes scales. Stochastic errors arising from diverse software execution within these…
Enabling users to create their own simulations offers a powerful way to study team dynamics and performance. We introduce VirTLab, a system that allows researchers and practitioners to design interactive, customizable simulations of team…
Virtualization, after having found widespread adoption in the server and desktop arena, is poised to change the architecture of embedded systems as well. The benefits afforded by virtualization - enhanced isolation, manageability,…
Fault tolerance is a property which needs deeper consideration when dealing with streaming jobs requiring high levels of availability and low-latency processing even in case of failures where Quality-of-Service constraints must be adhered…
Generating user activity is a key capability for both evaluating security monitoring tools as well as improving the credibility of attacker analysis platforms (e.g., honeynets). In this paper, to generate this activity, we instrument each…
CheckSync provides applications with high availability via runtime-integrated checkpointing. This allows CheckSync to take checkpoints of a process running in a memory-managed language (Go, for now), which can be resumed on another machine…
Modern vision-language-model (VLM) based graphical user interface (GUI) agents are expected not only to execute actions accurately but also to respond to user instructions with low latency. While existing research on GUI-agent security…
Graphical User Interface (GUI) action grounding is a critical step in GUI automation that maps language instructions to actionable elements on GUI screens. Most recent works of GUI action grounding leverage large GUI datasets to fine-tune…
General-purpose agents perform tasks in unfamiliar environments without domain-specific manual customization. Yet no study has systematically measured how agent architecture shapes performance across heterogeneous protocols and diverse…
Simulated user agents are increasingly used in usability testing to support fast, iterative UX workflows, as they generate rich data such as action logs and think-aloud reasoning, but the unstructured nature of this output often obscures…
When collaborating face-to-face, people commonly use the surfaces and spaces around them to perform sensemaking tasks, such as spatially organising documents, notes or images. However, when people collaborate remotely using desktop…
Modern AI systems, especially those interacting with the physical world, increasingly require real-time performance. However, the high latency of state-of-the-art generalist models, including recent vision-language action models (VLAs),…
Existing GUI agent models relying on coordinate-based one-step visual grounding struggle with generalizing to varying input resolutions and aspect ratios. Alternatives introduce coordinate-free strategies yet suffer from learning under…
We introduce SOCK, a benchmark command line interface (CLI) that measures large language models' (LLMs) ability to self-replicate without human intervention. In this benchmark, self-replication is defined not only as an LLM's ability to…
Computer-Using Agents (CUAs) aim to autonomously operate computer systems to complete real-world tasks. However, existing agentic systems remain difficult to scale and lag behind human performance. A key limitation is the absence of…
Automatically generating agentic workflows -- executable operator graphs or codes that orchestrate reasoning, verification, and repair -- has become a practical way to solve complex tasks beyond what single-pass LLM generation can reliably…
We investigate a multi-agent planning problem, where each agent aims to achieve an individual task while avoiding collisions with others. We assume that each agent's task is expressed as a Time-Window Temporal Logic (TWTL) specification…