{"slug": "llms-can-write-themselves-notes-to-get-better-at-reasoning", "title": "LLMs can write themselves notes to get better at reasoning", "summary": "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.", "body_md": "# Computer Science > Computation and Language\n\n[Submitted on 22 Jul 2026]\n\n# Title:Notes to Self: Can LLMs Benefit from Experiential Abstractions?\n\n[View PDF](/pdf/2607.20372)\n\n[HTML (experimental)](https://arxiv.org/html/2607.20372v1)\n\nAbstract: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.\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer\n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers\n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps\n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations\n\n*(*[What are Smart Citations?](https://www.scite.ai/))# Code, Data and Media Associated with this Article\n\nalphaXiv\n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers\n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub\n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub\n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face\n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast\n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower\n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender\n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth 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.\n\nHave an idea for a project that will add value for arXiv's community? [ Learn more about arXivLabs](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/llms-can-write-themselves-notes-to-get-better-at-reasoning", "canonical_source": "https://arxiv.org/abs/2607.20372", "published_at": "2026-07-24 14:09:33+00:00", "updated_at": "2026-07-24 14:22:40.046174+00:00", "lang": "en", "topics": ["large-language-models", "artificial-intelligence", "ai-research"], "entities": ["arXiv", "MATH training set"], "alternates": {"html": "https://wpnews.pro/news/llms-can-write-themselves-notes-to-get-better-at-reasoning", "markdown": "https://wpnews.pro/news/llms-can-write-themselves-notes-to-get-better-at-reasoning.md", "text": "https://wpnews.pro/news/llms-can-write-themselves-notes-to-get-better-at-reasoning.txt", "jsonld": "https://wpnews.pro/news/llms-can-write-themselves-notes-to-get-better-at-reasoning.jsonld"}}