AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

NitroGen: An Open Foundation Model for Generalist Gaming Agents

Loïc Magne, Anas Awadalla, Guanzhi Wang, Yinzhen Xu, Joshua Belofsky, Fengyuan Hu, Joohwan Kim, Ludwig Schmidt, Georgia Gkioxari, Jan Kautz, Yisong Yue, Yejin Choi and 2 more

CVPR 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: World-model-based agents · 27 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
pre-train on 40,000 hours of internet gameplay, then fine-tune on a held-out isometric roguelike (ablation)NitroGen 500M · Isometric roguelike (held-out game)task completion: average 10% relative improvement across data quantitiesImproved
pre-train on internet gameplay, then fine-tune on a held-out 3D action-RPG (ablation)NitroGen 500M · 3D action-RPG (held-out game)task completion: average 25% relative improvementImproved
pre-training on combat tasks of 3D action-RPG (ablation)NitroGen 500M · 3D action-RPG, 30h, combattask completion: 73.3% vs 48.3% (52% relative)Improved
pre-training on game-specific tasks of 3D action-RPG (ablation)NitroGen 500M · 3D action-RPG, 30h, game-specifictask completion: 66.6% vs 63.3% (5% relative)No clear effect
fine-tune on original BC data onlyNitroGen 500M · Boss 1 of 2D metroidvaniasuccess rate: 18.7% -> 30.1%Improved
add one round of self-imitation data (50/50 mix) (ablation)NitroGen 500M · Boss 1 of 2D metroidvaniasuccess rate: 30.1% -> 53.9%Improved
add three rounds of self-imitation (ablation)NitroGen 500M · Boss 1 of 2D metroidvaniasuccess rate: 53.9% -> 90.5%Improved
use more than one past frame as context, even with larger temporal gaps (ablation)NitroGen · game benchmarktask successNo clear effect
generate 16-action chunks instead of single actions (ablation)NitroGen · game benchmarktemporal consistencyImproved
keep only chunks with at least 50% non-zero actions (ablation)NitroGen training data · pre-trainingnull-action over-prediction: 55% of data keptImproved
predict joystick position via segmentation mask instead of direct regression (ablation)annotation model · action extractionjoystick accuracyImproved
use EMA weights instead of non-EMA weights (ablation)NitroGen · evaluationperformanceImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy