← back to paper

Review history

arxiv: 2605.11505 · 2 revisions

Selective Off-Policy Reference Tuning with Plan Guidance

1. 2026-05-14 UNVERDICTED LOW v0.9.0 novelty 6.0
   37534 ms 5391 in 1084 out 2026-05-14T21:17:08.782334+00:00
2. 2026-05-13 UNVERDICTED LOW v0.9.0 novelty 5.0
   58503 ms 5391 in 995 out 2026-05-13T01:24:17.316764+00:00