Search

直接匹配不多,已補上最新動態。

Tag: #rlcer1 results

RLCER Evolves CoT Rubrics

RLCER Evolves CoT Rubrics

RLCER reinforces chain-of-thought via self-evolving rubrics without human labels. Outperforms outcome-centric RLVR on reasoning tasks. Rubrics boost inference as prompts.

ArXiv AIResearchFeb 12#research#rlcer#v1