← back to paper

Review history

arxiv: 2607.18082 · 2 revisions

CriPO: Enhancing Rubric-based RL via Self-Distillation

1. 2026-08-04 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 6.0
   163747 ms 18548 in 13443 out 2026-08-04T04:09:51.703483+00:00
2. 2026-08-01 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 6.0
   490369 ms 18588 in 10384 out 2026-08-01T16:08:27.264751+00:00