← back to paper

Review history

arxiv: 2605.20246 · 2 revisions

GROW: Aligning GRPO with State-Action Modeling for Open-World VLM Agents

1. 2026-05-22 UNVERDICTED LOW v0.9.0 novelty 5.0
   47397 ms 5767 in 1282 out 2026-05-22T09:02:55.276742+00:00
2. 2026-05-21 CONDITIONAL LOW v0.9.0 novelty 6.0
   31279 ms 5767 in 1200 out 2026-05-21T08:37:49.738761+00:00