Notes to Self: Can LLMs Benefit from Experiential Abstractions?

TL;DR - LLMs improve mathematical and logical reasoning by distilling solution traces into reusable natural-language abstractions. The results suggest models can benefit from accumulated experience without relying on a stronger teacher.

• Abstractions are extracted from MATH solution traces into a retrievable library.
• The framework supports inference-time retrieval and abstraction-augmented RL training prompts.
• Self-extracted abstractions perform comparably to teacher-extracted ones.
• The approach transfers across datasets and models.