Teach Small Models to Reason by Curriculum Distillation

摘要

Large Reasoning Models (LRMs) show strong System-2-style reasoning, but at the cost of significant computational overhead. In contrast, efficient System-1-style Large Language Models (LLMs) often struggle on complex tasks. We identify a critical asymmetry between these two paradigms: LRMs can implicitly self-distill their own reasoning, solving hard problems with near System-1-style efficiency while retaining superior performance. LLMs, however, lack such deep internal modes and collapse when forced to rely on their own reasoning rather than imitating external traces. This asymmetry explains why direct distillation from strong LRMs to weaker LLMs often fails: student models struggle to learn from LRMs’ overly complex explicit reasoning and gain little from their overly compact implicit solutions. To address this, we introduce a two-stage curriculum distillation framework, which first builds a robust internal problem-solving student model and then teaches the student model to externalize this latent knowledge as explicit reasoning. On challenging mathematical benchmarks, our method significantly outperforms single-stage baselines, creating compact models with strong reasoning ability.