← back to paper

Review history

arxiv: 2607.25379 · 2 revisions

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response

1. 2026-08-04 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 5.0
   125785 ms 20269 in 10834 out 2026-08-04T01:24:50.079990+00:00
2. 2026-08-01 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 4.0
   130036 ms 19593 in 13987 out 2026-08-01T02:35:23.671103+00:00