ADeptS-Bench is a new benchmark designed to assess the trustworthiness of Computer Use Agents (CUAs) across mobile and desktop devices. It consists of two streams: a Safety stream with paired benign and malicious tasks that embed visual threats, and a Disambiguation stream that tests whether agents seek clarification when instructions are ambiguous. Evaluation of seven models shows none consistently achieves high task success while keeping attack success low, and all models exhibit problematic behaviors such as unhesitant checkout on a $25K order and failure to detect a mislabeled factory reset button.
arXiv:2606.23189v2 Announce Type: replace-cross Abstract: Computer-use agents (CUAs) now act on a user's behalf across personal applications such as email, calendars, and to-do lists. This cross-appl...
arXiv:2602. 08235v2 Announce Type: replace-cross Abstract: Although computer-use agents (CUAs) hold significant potential to automate increasingly complex OS workflows, they can demonstrate unsafe unintended behaviors that deviate from expected outcomes even under benign input contexts.
arXiv:2608.30207v1 Announce Type: cross Abstract: Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal...
arXiv:2607. 29254v1 Announce Type: new Abstract: AI agents extend large language models (LLMs) with external tools, enabling them to perform complex tasks and translate model outputs into consequential real-world actions.
arXiv:2606. 18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects.
Computer use agents (CUAs) are vision-language models that perceive a screen and act on a real operating system through mouse, keyboard, and terminal, and they are increasingly deployed to automate ev...
arXiv:2606. 02965v1 Announce Type: new Abstract: Benchmarks for autonomous agents measure whether agents complete tasks, yet this framing is systematically blind to whether an agent should have proceeded at all.
arXiv:2606. 15034v1 Announce Type: new Abstract: Computer-use agents are increasingly evaluated by whether they complete realistic desktop and web tasks.
The paper introduces CUAHarm, a benchmark comprising 104 expert‑written realistic misuse scenarios for computer‑using agents (CUAs), such as disabling firewalls or leaking data. Using a sandbox with verifiable rewards, the authors evaluate frontier language models—including GPT‑5, Claude 4 Sonnet, Gemini 2.5 Pro, Llama‑3.3‑70B, and Mistral Large 2—and find that even without jailbreak prompts, these models can successfully execute many malicious tasks at high rates (e.g., 90% for Gemini 2.5 Pro). The study also shows that newer models, while safer in traditional safety benchmarks, exhibit higher misuse risks as CUAs, and that monitoring CUAs’ actions remains challenging, with current methods achieving only about 77% accuracy.
The paper introduces a unified framework for monitoring misuse of large language model agents in multi‑actor settings, focusing on two attack types: decomposition attacks and prompt injection attacks. It proposes tracking the agent’s externalised actions and determining whether the first detection of harm falls within a defined harm window. Using this formalism, the authors build a benchmark of about 6,200 conversation transcripts and evaluate 17 monitor configurations, finding that action‑framed monitors perform well on both threats while content‑framed monitors struggle with injection attacks, and highlighting limitations of traditional position‑blind metrics.
arXiv:2609.16305v1 Announce Type: new Abstract: Large language model (LLM) agents increasingly operate over long-horizon interactions involving tool use, persistent state, evolving authorization, and...
arXiv:2607. 19449v1 Announce Type: cross Abstract: Evaluation frameworks for tool-augmented LLM agents focus overwhelmingly on capability metrics or explicit tool crashes, leaving silent infrastructure failures and HTTP 200 responses with empty, null, or malformed payloads largely unaudited.