JianxXiong/AAPO

Implementation of AAPO (Arxiv: 2505.14264v2) paper

27
/ 100
Experimental

This project offers an advanced reinforcement learning algorithm (AAPO) designed to significantly improve how large language models (LLMs) solve complex mathematical problems. It takes an existing LLM and training data for mathematical reasoning tasks, and outputs a fine-tuned LLM with enhanced accuracy and problem-solving capabilities. Researchers and practitioners working on AI models that require strong logical and mathematical abilities would find this beneficial.

Use this if you need to train or fine-tune large language models to achieve superior performance on mathematical reasoning benchmarks.

Not ideal if you are looking for a pre-trained, ready-to-use LLM without needing to engage in the training and evaluation process.

AI model training mathematical reasoning large language models machine learning research AI development
No Package No Dependents
Maintenance 6 / 25
Adoption 6 / 25
Maturity 15 / 25
Community 0 / 25

How are scores calculated?

Stars

16

Forks

Language

Python

License

MIT

Last pushed

Dec 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/JianxXiong/AAPO"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.