← back to paper

Review history

arxiv: 2605.21851 · 2 revisions

OPPO: Bayesian Value Recursion for Token-Level Credit Assignment in LLM Reasoning

1. 2026-05-25 UNVERDICTED LOW v0.9.0 novelty 6.0
   21188 ms 5847 in 1289 out 2026-05-25T05:45:58.239120+00:00
2. 2026-05-22 UNVERDICTED LOW v0.9.0 novelty 6.0
   40511 ms 5847 in 1191 out 2026-05-22T08:06:33.586996+00:00