← back to paper

Review history

arxiv: 2607.10139 · 2 revisions

LLMs as a Jury: Cross-Model Consensus Can Outperform Process Reward Models for LLM Reasoning

1. 2026-08-02 CONDITIONAL MODERATE v1.3.0-alltime-deepseek novelty 6.0
   187146 ms 25144 in 19466 out 2026-08-02T07:21:18.607023+00:00
2. 2026-07-14 CONDITIONAL HIGH v1.1.0-grok45 novelty 6.0
   36382 ms 31012 in 3904 out 2026-07-14T13:59:28.340651+00:00