Pith. sign in

← back to paper

Review history

arxiv: 2607.02818 · 2 revisions

Session-Level Optimization for Large-Scale Retrieval using REINFORCE with Multi-Step Off-Policy Correction

  1. 2026-08-02 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 5.0
    205012 ms 15228 in 21136 out 2026-08-02T08:55:01.572864+00:00
  2. 2026-07-12 CONDITIONAL HIGH v1.1.0-grok45 novelty 5.5
    33751 ms 21117 in 3309 out 2026-07-12T06:50:19.320351+00:00