‹ back to 2026-07-23

Notes to Self: Can LLMs Benefit from Experiential Abstractions?

Research LLMs & Foundation Models

Merged summary

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.

Sources (1)

Notes to Self: Can LLMs Benefit from Experiential Abstractions?

arXiv cs.CL Chang Liu, Xinyu Li, Artur Dubrawski 2026-07-22 arXiv:2607.20372

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.

item →