A Roadmap to Build World Models for Robot Policy Evaluation

Code for MIRA: Multiplayer Interactive World Models with Representation Autoencoders

A Python port of Pi’s minimalist coding agent.

OSCAR — public inference release

Convert any Repo into an RL Environment

A community curated collection of AI agent failure modes and battle-tested solutions.

🚀 An open-source, hands-on curriculum bridging the gap from basic RL concepts to LLM alignment, RLVR, and advanced Agentic systems.

RLAnything (ICML 2026) & AutoTool (ICML 2026), DemyAgent: Open-Source RL for LLMs and Agentic Scenarios

Sim2Reason: Solving Physics Olympiad via Reinforcement Learning on Physics Simulators. We present a method for turning physics simulators into scalable generators of question–answer pairs for impro…

[NeurIPS 2025 D&B Spotlight] Scaling Data for SWE-agents

SWE-Bench-plus-plus

A Minimalist, Batteries-included Repository for Advancing World Model Science.

[ICML 2026] World-R1: Reinforcing 3D Constraints for Text-to-Video Generation

An interface library for RL post training with environments.

verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

Official Implementation of MultiWorld: Scalable Multi-Agent Multi-View Video World Models

🌱 A little course on Reinforcement Learning Environments for evaluating and training Language Models

(ICLR2025) Enhancing End-to-End Autonomous Driving with Latent World Model

A Collection of Competitive Text-Based Games for Language Model Evaluation and Reinforcement Learning

Reinforcement Learning environments for Traffic Signal Control with SUMO. Compatible with Gymnasium, PettingZoo, and popular RL libraries.

[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards

Our library for RL environments + evals

PhD/MBA-level human-annotated rubrics dataset across Physics, Chemistry, Finance and Consulting

A feed-forward 3D foundation model for reconstructing scenes from streaming data

[ECCV 2026] Official Implementation of Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction

A Python framework for AI-driven character animation using neural networks.

Official code base for LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds