← back to paper

Review history

arxiv: 2605.11461 · 2 revisions

Breaking $\textit{Winner-Takes-All}$: Cooperative Policy Optimization Improves Diverse LLM Reasoning

1. 2026-05-20 UNVERDICTED LOW v0.9.0 novelty 7.0
   55765 ms 5793 in 1392 out 2026-05-20T22:42:29.577145+00:00
2. 2026-05-13 UNVERDICTED LOW v0.9.0 novelty 7.0
   35284 ms 5566 in 1366 out 2026-05-13T01:53:17.683923+00:00