arXiv: cs.AI preprintsInternational19 November 2026
SEAM: Computer-Use Agents Know the Harm Between Screens, and Commit It Anyway
This is an official announcement record
Firsthand records what arXiv: cs.AI preprints announced and links to the original. The wording below is theirs, not ours.
arXiv:2611.22971v1 Announce Type: cross 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
Read the official announcement
Opens arxiv.org
More from arXiv: cs.AI preprints
- Human-AI Mutualism Is Unstable under Capability Asymmetry20 November 2026
- Training Language Models for Introspective Oversight20 November 2026
- Where the Tokens Go: Heat, Entropy and Error in Agentic Coding20 November 2026
- HardwareDx: A Foundational Graph Model System for Datacenter Machine Repairs20 November 2026
- RFBench: A Simulator-Grounded Multimodal Benchmark for Passive RF Layout Design and Understanding20 November 2026
This content is for informational purposes only and is not professional advice. Specifications, prices, plan tiers, and features change frequently and may differ from what is shown here; verify current details on the manufacturer's or company's official page before purchasing. Ratings are based on analysis of published documentation, not independent lab testing.