arXiv cs.AI· Yuxuan Zhou, Chen Xiong, Haitong Liu, Kuofeng Gao, Yang Bai, Zhiyuan He, Tao Dai, Shu-Tao Xia·· 23 小时前AI 评分58
SEAM:电脑操作智能体识别跨屏组合风险后仍会执行
SEAM: Computer-Use Agents Know the Harm Between Screens, and Commit It Anyway
AI 导读
研究者提出 SEAM 基准,包含 600 个跨应用、多步骤的 OSWorld 任务,指令和每一步观察单独看都无害,只有组合起来才构成危害。通用开源权重模型和旗舰智能体在最多 92% 的运行中执行了这类危害,但用户用一句话直接说明时它们会拒绝;智能体确实打开了关键页面,被问及时也能指出危害,思考模式下常把冲突写进推理却仍然确认执行。
正文 · 原文
Abstract:Safety benchmarks for computer-use agents (CUAs) place the harm either in the intent of the task or on a single screen: a malicious instruction, an injected command, a phishing page. An agent that checks the task and each screen in isolation can pass them, so they do not test whether it combines facts seen on different screens. Yet in delegated work, harm often arises exactly this way: a fact about a person on one screen, a fact about an item on another, and a legitimate task that binds them. We introduce SEAM (Safety Execution Across Multiple screens), a benchmark of such cross-screen compositional harm: 600 multi-step, cross-application OSWorld tasks in which the instruction and every single observation are benign and only their combination is harmful. Minimal-pair variants that differ in one place, scored from the server log rather than by an LLM judge, locate where an agent fails. General-purpose open-weight and flagship agents carry out the harm in up to 92% of runs, yet decline when the user states it in one sentence. Agents open the decisive pages, so exposure is not the primary bottleneck. Asked about those pages, they flag the harm, and with thinking they often write the conflict into their reasoning and confirm anyway. Safety recognition thus does not reliably translate into safe execution, and the translation depends on the information channel: the same warning stops agents far more often in the user's instruction than on screen. Proprietary models are markedly more cautious. We release SEAM with its generator and quality gates at this https URL .
| Comments: | 30 pages, 14 figures, 29 tables |
| Subjects: | Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI) |
| ACM classes: | I.2.7; I.2.10 |
| Cite as: | arXiv:2611.22971 [cs.CR] |
| (or arXiv:2611.22971v1 [cs.CR] for this version) | |
| https://doi.org/10.48550/arXiv.2611.22971 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Yuxuan Zhou [view email]
[v1]
Tue, 17 Nov 2026 15:53:58 UTC (915 KB)
来源:arXiv cs.AI · arxiv.org