Pith. sign in

← back to paper

Review history

arxiv: 2509.02522 · 2 revisions

Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR

  1. 2026-08-15 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 5.0
    160166 ms 16788 in 17818 out 2026-08-15T16:37:57.582219+00:00
  2. 2026-08-05 CONDITIONAL MODERATE v1.4.0-alltime-deepseek-medium novelty 4.0
    179830 ms 16805 in 18512 out 2026-08-05T11:33:16.350220+00:00