WooooDyy/LLM-Reverse-Curriculum-RL
Implementation of the ICML 2024 paper "Training Large Language Models for Reasoning through Reverse Curriculum Reinforcement Learning" presented by Zhiheng Xi et al.
This project helps machine learning researchers improve how Large Language Models (LLMs) reason and solve complex problems. By applying a "reverse curriculum" reinforcement learning approach, it takes an existing LLM and outputs a new, fine-tuned LLM that is better at tasks requiring step-by-step logical thought, such as mathematical problem-solving or understanding nuanced text. It's designed for AI/ML researchers and practitioners focused on advanced LLM training techniques.
116 stars. No commits in the last 6 months.
Use this if you are a machine learning researcher or engineer looking to enhance the reasoning capabilities of Large Language Models for complex tasks through advanced training methodologies.
Not ideal if you are an end-user simply looking to apply an existing LLM for standard tasks without deep technical involvement in model training and optimization.
Stars
116
Forks
10
Language
Python
License
—
Category
Last pushed
Feb 09, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/WooooDyy/LLM-Reverse-Curriculum-RL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cvs-health/uqlm
UQLM: Uncertainty Quantification for Language Models, is a Python package for UQ-based LLM...
PRIME-RL/TTRL
[NeurIPS 2025] TTRL: Test-Time Reinforcement Learning
sapientinc/HRM
Hierarchical Reasoning Model Official Release
tigerchen52/query_level_uncertainty
query-level uncertainty in LLMs
reasoning-survey/Awesome-Reasoning-Foundation-Models
✨✨Latest Papers and Benchmarks in Reasoning with Foundation Models