Trendoday

Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent

We introduce Gamer, a generalist agent framework built for long-horizon tasks in complex interactive environments. Its end-to-end architecture combines perception, memory management, and multi-step re

  • Upvotes20
–Rank now
#2Peak rank
2Days on list
377Score · 7d
Nov 16, 2026First seen
Rank · 7 days

About this paper

Gamer is a generalist agent framework that integrates perception, memory, and multi-step reasoning, trained through continued pre-training, sparse-thinking instruction tuning, and multi-turn reinforcement learning to interact efficiently in 2D and 3D environments.

We introduce Gamer, a generalist agent framework built for long-horizon tasks in complex interactive environments. Its end-to-end architecture combines perception, memory management, and multi-step reasoning. A shared training and deployment pipeline supports interaction with both conventional 2D graphical interfaces and complex 3D simulated worlds. We first continue pre-training on a dataset constructed from tens of thousands of hours of device-level keyboard and mouse interaction. These trajectories span simulated games and embodied environments, allowing the model to learn environmental dynamics across both physical and virtual domains. Sparse-thinking instruction tuning then…

generalist agent frameworklong-horizon tasksend-to-end architectureperceptionmemory managementmulti-step reasoningcontinue pre-trainingembodied environmentsenvironmental dynamicssparse-thinking instruction tuning
Upvotes
20
Authors
27
Published
Nov 13, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent was first seen on Hugging Face · Daily papers on Nov 16, 2026. Since then it has appeared in 14 checks on 2 different days. Its best position was #2 of 30, reached on Nov 16, 17:28 UTC. It dropped off the list after Nov 17, 07:28 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 05:2811:5818:2800:5807:28 Nov 16, 05:28 UTC · #13Nov 16, 07:28 UTC · #3Nov 16, 09:28 UTC · #3Nov 16, 11:28 UTC · #4Nov 16, 13:28 UTC · #4Nov 16, 15:28 UTC · #3Nov 16, 17:28 UTC · #2Nov 16, 19:28 UTC · #2Nov 16, 21:28 UTC · #2Nov 16, 23:28 UTC · #2Nov 17, 01:28 UTC · #2Nov 17, 03:28 UTC · #2Nov 17, 05:28 UTC · #2Nov 17, 07:28 UTC · #2

Last 14 days

Best rank per day (UTC).

Nov 9today

Metric history

Platform metric as reported by Hugging Face.

03366100 05:2811:5818:2800:5807:28 Nov 16, 05:28 UTC · 18Nov 16, 07:28 UTC · 48Nov 16, 09:28 UTC · 61Nov 16, 11:28 UTC · 63Nov 16, 13:28 UTC · 68Nov 16, 15:28 UTC · 75Nov 16, 17:28 UTC · 86Nov 16, 19:28 UTC · 87Nov 16, 21:28 UTC · 87Nov 16, 23:28 UTC · 87Nov 17, 01:28 UTC · 88Nov 17, 03:28 UTC · 90Nov 17, 05:28 UTC · 95Nov 17, 07:28 UTC · 100

Questions

Is Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 17, 07:28 UTC, after 2 days of trending.

What is the highest rank Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent reached?

#2 on Hugging Face · Daily papers, on Nov 16, 17:28 UTC. Trendoday checks this list every 120 minutes.

How long has Gamer: A Generalist Vision-Language-Action Foundation Model for Long-Horizon Real-Time Game Agent been trending?

It was first seen on Nov 16, 2026 and has been on the list on 2 days (14 checks) since.