pith. sign in

← back to paper

Review history

arxiv: 2605.22643 · 2 revisions

Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety

  1. 2026-05-25 UNVERDICTED LOW v0.9.0 novelty 7.0
    65781 ms 5874 in 1383 out 2026-05-25T06:02:18.911161+00:00
  2. 2026-05-22 UNVERDICTED LOW v0.9.0 novelty 7.0
    52848 ms 5874 in 1333 out 2026-05-22T05:46:41.215851+00:00