Run Luo, Kuan Zhang, Qi Deng, Yukun Chen, Zhihao Yang, Yufei Zhang, Renrong Hu, Yi Zhang (arXiv) · Game VLA Agent
Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent
Gamer is a generalist agent framework for long-horizon tasks in interactive environments, combining perception, memory management and multi-step reasoning. It is pre-trained on tens of thousands of hours of device-level keyboard and mouse trajectories from simulated games and embodied environments, then tuned with sparse-thinking instruction tuning and multi-turn reinforcement learning. The authors report solid generalisation across several 3D open-world games, efficiency comparable to skilled players, and competitive results on conventional 2D game benchmarks.
Open the source ↗Similar Agents & Automation releases
- Mage-VL-Cowork
Microsoft Mage Team · Hybrid CUA Agent · Week 46, 2026
- Flash ALOHA: Learning Fast and Precise Manipulation
Flash ALOHA project authors (project page by John Yao and collaborators) · Fast robot imitation learning · Week 47, 2026
- LingBot-Touch
Robbyant (Ant Group) · Tactile foundation model · Week 47, 2026
- Cindy
makecindy · Multi-device agent client · Week 47, 2026
- Rakazo
Elie Steinbock (elie222) · Self-hosted AI teammates · Week 47, 2026
- blender-ai-copilot-forge
Doug-218 (GitHub) · Blender AI Copilot · Week 47, 2026
Published by Quanta AI Labs, an AI agency in India. Browse every week in AI News Weekly.