Gamer paper presents a vision-language-action model for game agents
First seen Nov 16 Updated Nov 16, 11:44 UTC Heat 14 medium evidence
A Hugging Face papers entry introduces Gamer, a vision-language-action framework for game agents on long, real-time tasks. It combines perception, memory management and multi-step reasoning end to end. Training starts with continued pre-training on tens of thousands of hours of keyboard and mouse interaction data, followed by sparse-thinking instruction tuning and multi-turn reinforcement learning.
- Who should care
- Researchers building game or computer-use agents.
Key facts
- Covers 2D graphical interfaces and 3D simulated worlds
Timeline
Coverage
-
Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agenthuggingface.co · HF Papers · 2 comments · 124 stars
Evidence
Medium evidence: several community reports point the same way, but there is no official confirmation yet.
Details written Nov 16, 06:25 UTC from the sources listed above.