Home Projects cumulative-reasoning
cumulative-reasoning
Python

cumulative-reasoning

[TMLR] Cumulative Reasoning With Large Language Models (https://arxiv.org/abs/2308.04371)

by iiis-ai · GitHub
Stars
Forks
Created
Last commit
Language
large-language-modelsllmmathPython
View on GitHub
In plain words

Use a structured approach to solve complex problems with large language models by breaking tasks into smaller steps.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
cumulative-reasoning — GitHub preview card
📈 Star history
309308
2026-07-202026-08-31
📈 Track cumulative-reasoning

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

[TMLR] Cumulative Reasoning With Large Language Models (https://arxiv.org/abs/2308.04371)

cumulative-reasoning has 308 stars on GitHub. It has been forked 36 times. cumulative-reasoning is written mainly in Python. It has been in active development since 2023. Its main topics are large-language-models, llm, math, prompting.

Frequently asked questions

What is cumulative-reasoning?

[TMLR] Cumulative Reasoning With Large Language Models (https://arxiv.org/abs/2308.04371)

Is cumulative-reasoning open source?

cumulative-reasoning is an open-source project.

Is cumulative-reasoning free?

Yes. cumulative-reasoning is free and open source — you can use, modify and self-host it.

What language is cumulative-reasoning written in?

cumulative-reasoning is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — cumulative-reasoning

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=iiis-ai-cumulative-reasoning)](https://olud.ai/project/iiis-ai-cumulative-reasoning.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.