cd /news/large-language-models/llms-can-write-themselves-notes-to-g… · home topics large-language-models article
[ARTICLE · art-72079] src=arxiv.org ↗ pub= topic=large-language-models verified=true sentiment=· neutral

LLMs can write themselves notes to get better at reasoning

A new study on arXiv shows that large language models (LLMs) can improve their reasoning by writing and retrieving natural-language notes, or 'experiential abstractions,' from their own solution traces. Researchers found that self-extracted abstractions matched teacher-extracted ones in boosting performance on math and logic benchmarks, and the framework transfers to other datasets and models.

read2 min views1 publishedJul 24, 2026
LLMs can write themselves notes to get better at reasoning
Image: source
[Submitted on 22 Jul 2026]


[View PDF](/pdf/2607.20372)

[HTML (experimental)](https://arxiv.org/html/2607.20372v1)

Abstract:Humans distill experience into reusable abstractions, e.g., strategies and cautionary reminders, and apply them to gradually solve problems more effectively. We study whether Large Language Models (LLMs) can similarly benefit from such experiential abstractions. From LLMs' solution traces on the MATH training set, a stronger teacher or the LLMs themselves extract natural-language abstractions into a retrievable library. We explore two usage modes: (1) inference-time retrieval and (2) reinforcement learning (RL) with abstraction-augmented training prompts. Experiential abstractions improve LLM performance on mathematical and logical reasoning benchmarks. Self-extracted abstractions match teacher-extracted ones, and our abstraction usage framework can transfer to other datasets and models. These findings suggest LLMs can extract and apply experiential abstractions much as humans leverage distilled experience.

References & Citations

...

Bibliographic Explorer

(What is the Explorer?) Connected Papers

(What is Connected Papers?) Litmaps

(What is Litmaps?) scite Smart Citations

(What are Smart Citations?)# Code, Data and Media Associated with this Article alphaXiv

(What is alphaXiv?) CatalyzeX Code Finder for Papers

(What is CatalyzeX?) DagsHub

(What is DagsHub?) Gotit.pub

(What is GotitPub?) Hugging Face

(What is Huggingface?) ScienceCast

(What is ScienceCast?)# Demos Influence Flower

(What are Influence Flowers?) CORE Recommender

(What is CORE?)# arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

── more in #large-language-models 4 stories · sorted by recency
── more on @arxiv 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/llms-can-write-thems…] indexed:0 read:2min 2026-07-24 ·