Skip to content
Log in

Author

Cheng Qian

View on Semantic Scholar

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Jul 2026

Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning

MetaEvolve is presented, a framework designed to develop meta-skills that can transfer broadly to open-ended problems where such rich training signals are scarce, and aims to inspire generalizable domain-agnostic meta-skills that can transfer broadly to open-ended problems where such rich training signals are scarce.

Shujin Wu, Cheng Qian, Xiusi Chen et al. · 0 citations