GTAGym: AAA Game Tasks Environment for Evaluation and Reinforcement Learning
cs.CV, cs.AI, cs.CL
Submitted: 2026-11-09
Updated: 2026-11-11
Code: https://github.com/ljbro/GTAGym
Terminology
Sources
- SIMA 2: A Generalist Embodied Agent for Virtual Worlds
- LoRA: Low-Rank Adaptation of Large Language Models
- OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Cradle: Empowering Foundation Agents Towards General Computer Control
- Lumine: An Open Recipe for Building Generalist Agents in 3D Open Worlds
- GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay
- VideoGameBench: Can Vision-Language Models complete popular video games?
- LongPuzzleBench: Evaluating GUI Agents on Long-Horizon Visual Puzzles
- GameVerse: Can Vision-Language Models Learn from Video-based Reflection?
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs