Asymmetric Capacity Allocation in Self-Refinement Pipelines

By Zhuoyi Yang · Paper · cs.LG

Self-refinement, typically structured as generation, critique, and revision, is a widely adopted paradigm for improving LLM generation and serves as a core mechanism in many LLM agents. While the three stages involve different cognitive demands, most existing approaches convenien

Cs.lg

View original

HomeResourceLoading…