AI RESEARCH

ReAD: Reinforcement-Guided Capability Distillation for Large Language Models

arXiv CS.AI

ArXi:2605.11290v1 Announce Type: cross Capability distillation applies knowledge distillation to selected model capabilities, aiming to compress a large language model (LLM) into a smaller one while preserving the abilities needed for a downstream task. However, most existing methods treat capabilities as independent