AIWHYS

Products

OSWorld

2 synchronized stories carry this tag.

ReliabilityPreprint

More inference compute does not reliably rescue local computer-use agents

Researchers tested longer context, longer trajectories, task decomposition and parallel attempts for selected Qwen3-VL, UI-TARS and OpenCUA models on OSWorld. Extra context saturated, long runs prolonged some wrong paths, decomposition added overhead and parallel attempts were expensive.

Why it matters: More steps and context can spend additional compute on the same mistaken plan. Reliability needs failure detection and selective escalation, not an unrestricted execution budget.

Read storyOriginal source · arxiv.org
ReliabilityPreprint

OSGuard finds a gap between isolated safety checks and safe end-to-end computer use

The OSGuard preprint introduces action-level and live OSWorld evaluations containing latent hazards, reporting that guardrails which look strong in isolation can still fail when embedded in complete computer-use trajectories.

Why it matters: Agent safety must be evaluated at the action and trajectory level, where harmless-looking individual steps can combine into a dangerous outcome.

Read storyOriginal source · arxiv.org