Understanding R1-Zero-Like Training: A Critical Perspective

Research Code for preprint "Optimizing Test-Time Compute via Meta Reinforcement Finetuning".

[Support 0.48.x]（Reset Cursor AI MachineID & Bypass Higher Token Limit） Cursor Ai ，自动重置机器ID ， 免费升级使用Pro功能: You've reached your trial request limit. / Too many free trial accounts used on this machi…

A lightweight, powerful framework for multi-agent workflows

Recipes to train the self-rewarding reasoning LLMs.

Democratizing Reinforcement Learning for LLMs

This is the official implementation of the paper "S²R: Teaching LLMs to Self-verify and Self-correct via Reinforcement Learning"

Muon is Scalable for LLM Training

Production-tested AI infrastructure tools for efficient AGI development and community-driven innovation

Official Repo for Open-Reasoner-Zero

Paper Reproduction Google SCoRE(Training Language Models to Self-Correct via Reinforcement Learning)

MR.Q is a general-purpose model-free reinforcement learning algorithm.

Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

Extreme Q-Learning: Max Entropy RL without Entropy

verl: Volcano Engine Reinforcement Learning for LLMs

Awesome lists about framework figures in papers

Clean, minimal, accessible reproduction of DeepSeek R1-Zero

My learning notes/codes for ML SYS.

Simple RL training for reasoning

Fully open reproduction of DeepSeek-R1

NeurIPS 2024 tutorial on LLM Inference

Make websites accessible for AI agents

Repository for the paper Stream of Search: Learning to Search in Language

Eko (Eko Keeps Operating) - Build Production-ready Agentic Workflow with Natural Language - eko.fellou.ai

Automating the Search for Artificial Life with Foundation Models!

Clean single-file implementation of offline RL algorithms in JAX

Scalable RL solution for advanced reasoning of language models

Recipes to scale inference-time compute of open models