[2607.20372] Notes to Self: Can LLMs Benefit from Experiential Abstractions?
Skip to main content
Search arXiv
Press Enter to search · Advanced search
-->
Computer Science > Computation and Language
arXiv:2607.20372 (cs)
[Submitted on 22 Jul 2026]
Title:Notes to Self: Can LLMs Benefit from Experiential Abstractions?
Authors:Chang Liu, Xinyu Li, Artur Dubrawski<br>View a PDF of the paper titled Notes to Self: Can LLMs Benefit from Experiential Abstractions?, by Chang Liu and 2 other authors
View PDF<br>HTML (experimental)
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.
Subjects:
Computation and Language (cs.CL)
Cite as:<br>arXiv:2607.20372 [cs.CL]
(or<br>arXiv:2607.20372v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2607.20372
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history<br>From: Chang Liu [view email]<br>[v1]<br>Wed, 22 Jul 2026 17:02:34 UTC (94 KB)
Full-text links:<br>Access Paper:
View a PDF of the paper titled Notes to Self: Can LLMs Benefit from Experiential Abstractions?, by Chang Liu and 2 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source
view license
Current browse context:
cs.CL
next >
new<br>recent<br>| 2026-07
Change to browse by:
cs
References & Citations
NASA ADS<br>Google Scholar
Semantic Scholar
export BibTeX citation<br>Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
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 .
Which authors of this paper are endorsers? |<br>Disable MathJax (What is MathJax?)
Major funding support from