pith. sign in

← back to paper

Review history

arxiv: 2605.09730 · 3 revisions

RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement

  1. 2026-05-20 UNVERDICTED LOW v0.9.0 novelty 7.0
    44235 ms 5739 in 1300 out 2026-05-20T22:08:27.045816+00:00
  2. 2026-05-15 UNVERDICTED LOW v0.9.0 novelty 7.0
    53030 ms 5519 in 1497 out 2026-05-15T05:21:43.945619+00:00
  3. 2026-05-12 UNVERDICTED LOW v0.9.0 novelty 6.0
    44381 ms 5519 in 1388 out 2026-05-12T03:29:03.016521+00:00