chi2liu/ABC-GRPO

[ICLR 2026] Agentic Reinforced Policy Optimization (ARPO)

An Open-source RL System from ByteDance Seed and Tsinghua AIR

📄Score Centering Stabilizes Off-policy Reinforcement Learning

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

[Neurips 2026] Official repository for the paper "Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models"

Reproducing and studying RL algorithms for LLM agents, including GRPO, GSPO, DAPO, OPD, Search-R1, ReTool, ALFWorld and beyond.

[NeurIPS 2024] SimPO: Simple Preference Optimization with a Reference-Free Reward

A repo for distributed training of language models with Reinforcement Learning via Human Feedback (RLHF)