← back to paper

Review history

arxiv: 2508.19488 · 2 revisions

PoolFlip: A Multi-Agent Reinforcement Learning Security Environment for Cyber Defense

1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   155814 ms 14617 in 17554 out 2026-08-15T16:52:49.280368+00:00
2. 2026-08-05 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 6.0
   120796 ms 14644 in 12935 out 2026-08-05T15:44:29.362393+00:00