← back to paper

Review history

arxiv: 2605.10067 · 3 revisions

Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization

1. 2026-05-22 UNVERDICTED LOW v0.9.0 novelty 6.0
   39830 ms 5790 in 1397 out 2026-05-22T10:42:13.178257+00:00
2. 2026-05-14 UNVERDICTED LOW v0.9.0 novelty 7.0
   44210 ms 5559 in 1298 out 2026-05-14T20:46:23.945934+00:00
3. 2026-05-12 UNVERDICTED LOW v0.9.0 novelty 6.0
   53572 ms 5559 in 1279 out 2026-05-12T04:52:37.412580+00:00