BAGEN is a framework for evaluating, training, and understanding budget-aware agents.

Scale digital agent rollouts without pain.

RAGEN leverages reinforcement learning to train LLM reasoning agents in interactive, stochastic environments.

Trajectory optimization methods for improving LLM agents via weak-to-strong learning.

Nano vLLM

A paper list for spatial reasoning

[ICLR 2026] LLM/VLM gaming agents and model evaluation through games.

TStar is a unified temporal search framework for long-form video question answering

World model reasoning RL for multi-turn VLM agents

MoBA: Mixture of Block Attention for Long-Context LLMs

Code release for DynamicTanh (DyT)

Autoregressive Entity Retrieval

Chain of Experts (CoE) enables communication between experts within Mixture-of-Experts (MoE) models

FlashMLA: Efficient Multi-head Latent Attention Kernels

Official Repo for Open-Reasoner-Zero

Kodu is an autonomous coding agent that lives in your IDE. It is a VSCode extension that can help you build your dream project step by step by leveraging the latest technologies in automated coding…

Solve puzzles. Improve your pytorch.

Awesome-LLM: a curated list of Large Language Model

Sokoban environment for OpenAI Gym

A system that tries to resolve all issues on a github repo with OpenHands.

Deep learning for dummies. All the practical details and useful utilities that go into working with real models.

The hub for EleutherAI's work on interpretability and learning dynamics

Janus-Series: Unified Multimodal Understanding and Generation Models

Code for the manim-generated scenes used in 3blue1brown videos