meta-prompting/meta-prompting
Official implementation of Meta Prompting for AI Systems (https://arxiv.org/abs/2311.11482)
This project introduces Meta Prompting, a framework that helps AI system developers and researchers improve how large language models (LLMs) reason through complex problems. Instead of providing specific examples, it uses a high-level, structural template to guide the LLM's thinking process. By giving an LLM a meta-prompt (a general blueprint for problem-solving), you get more accurate and efficient results on tasks like mathematical problem-solving, without needing lots of examples or fine-tuning.
286 stars.
Use this if you are an AI researcher or developer looking to enhance the reasoning abilities of LLMs on complex, multi-step tasks, and want to achieve better performance with fewer tokens and without extensive fine-tuning or few-shot examples.
Not ideal if you are a casual user simply looking to generate text or if your primary interest is in simple, straightforward LLM applications that don't require complex, structured reasoning.
Stars
286
Forks
33
Language
Python
License
MIT
Category
Last pushed
Dec 23, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/meta-prompting/meta-prompting"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
auniquesun/Point-PRC
[NeurIPS 2024] Official implementation of the paper "Point-PRC: A Prompt Learning Based...
slashrebootofficial/simulated-metacognition-in-open-source-llms
This repository archives artifacts (prompts, configs, logs, and scripts) from a series of...
UKPLab/emnlp2024-code-prompting
Code Prompting Elicits Conditional Reasoning Abilities in Text+Code LLMs. EMNLP 2024
egmaminta/GEPA-Lite
A lightweight implementation of the GEPA (Genetic-Pareto) prompt optimization method for large...
Techolution/LazyLM
A prompting framework for getting foundational models to “lazily” evaluate their reasoning trace