← back to paper

Review history

arxiv: 2603.22169 · 2 revisions

VersualRL: Closed-Loop Verbal Reinforcement Learning with Visual Execution Feedback for Task-Level Robot Planning

1. 2026-08-02 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 5.0
   103010 ms 8941 in 10193 out 2026-08-02T17:36:01.093541+00:00
2. 2026-07-13 CONDITIONAL MODERATE v1.1.0-grok45 novelty 5.5
   40722 ms 19279 in 2940 out 2026-07-13T20:22:14.963970+00:00