AI Science Tracker
EN

ScamWorld documents a recognition-to-action gap in web-agent fraud scenarios

Deakin University; Fudan University; The University of Melbourne; Amazon; Shanghai Innovation Institute · 3 Nov 2026 · computer science

Discovery

ScamWorld documents a recognition-to-action gap in web-agent fraud scenarios

Source check: Source checked. Not independent scientific confirmation.

Finding: The study reports cases where agents recognized warning cues but still proceeded with the requested action in evaluated scenarios. This is a bounded agent-behavior benchmark; it does not provide or validate methods for committing fraud or establish outcomes in live services.

Technology: Six web-agent models were evaluated in controlled reconstructed websites; outcomes were classified from site event logs.

Publication: Preprint · Test context: retrospective or benchmark. Catalog categories, not an evidence grade.

AI contribution
Six web-agent models were evaluated in controlled reconstructed websites; outcomes were classified from site event logs.
Test and result
The study reports cases where agents recognized warning cues but still proceeded with the requested action in evaluated scenarios.
Limitation / still unknown
This is a bounded agent-behavior benchmark; it does not provide or validate methods for committing fraud or establish outcomes in live services.
Evidence sources and annotation context

Evidence context (descriptions follow the cited sources; test type is a catalog classification):

Evidence sources: https://arxiv.org/html/2611.04879v1

Source checked · editorial details

The source page was checked against this entry. Independent confirmation is not assessed by this label.

Source type: paper. Paper: not linked in this catalog; this does not mean no paper exists.

Review date: 22 Nov 2026. Review scope: Primary result-bearing material for the stated method, result and evaluation, with bibliographic version information..

No follow-up recorded; this is not a claim that no follow-up exists. Follow-up review scope and date are not recorded. No source-supported relationships recorded.

Editorial assessment: Impact 2/5 · Validation 2/5 · Novelty 2/5. Impact and novelty are editorial judgments; validation follows the annotated test type where one exists. Not an evidence grade. Scoring criteria.

Open in the full catalog for filters, charts and related discoveries. Browse computer science discoveries.