spade-rl/spade

Democratizing Reinforcement Learning for LLMs

Open Source LLM Reinforcement Learning Framework for MLGym Environments 2026

Official Repo for SvS: A Self-play with Variational Problem Synthesis strategy for RLVR training

Atropos is a Language Model Reinforcement Learning Environments framework for collecting and evaluating LLM trajectories through diverse environments

Fine-tune LLM agents with online reinforcement learning

Drift: DLM Reinforcement Learning Training Framework

[NeurIPS 2026] GenEnv: Difficulty-Aligned Co-Evolution Between LLM Agents and Environment Simulators

The official implementation of "EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis".