Browser agents need to make decisions and execute actions on behalf of users while consuming untrusted webpages, creating opportunities for malicious instructions embedded in webpages to redirect legitimate tasks. We introduce BrowseSafe++, which extends BrowseSafe from 14,719 pages to 38,675 pairs of pages. Most of it...
Yue-Tian Chen, Kai-Yuan Zhang, Yun-Tao Du et al.· 0 citations
This work introduces PII-Tracer, a compact 0.6B-parameter detector trained with conversation-level supervision that attains the highest entity-level coverage of any system the authors evaluate and also performs strongly on standard single-record benchmarks.
Kai-Yuan Zhang, Chuan Wang, Joey Zhong et al.· 0 citations
WANDR (Wide ANd Deep Research) is a benchmark of 500 realistic, challenging data-collection tasks for research agents that replaces static gold answer sets with task-specific judges that refetch cited pages and verify each record against its evidence, allowing evaluation of current and changing facts.
Vitaliy Polshkov, Marcin Pitera, Jeremy Yang et al.· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.