JianxXiong/AAPO
Implementation of AAPO (Arxiv: 2505.14264v2) paper
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.
Stars
16
Forks
—
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
PaddlePaddle/PaddleNLP
Easy-to-use and powerful LLM and SLM library with awesome model zoo.
meta-llama/llama-cookbook
Welcome to the Llama Cookbook! This is your go to guide for Building with Llama: Getting started...
arcee-ai/mergekit
Tools for merging pretrained large language models.
changyeyu/LLM-RL-Visualized
๐100+ ๅๅ LLM / RL ๅ็ๅพ๐๏ผใๅคงๆจกๅ็ฎๆณใไฝ่ ๅทจ็ฎ๏ผ๐ฅ๏ผ100+ LLM/RL Algorithm Maps ๏ผ
mindspore-lab/step_into_llm
MindSpore online courses: Step into LLM