AceAction-5M: Hierarchical Goals for Generalist Action Learning Across 3D Game Worlds
cs.AI
Submitted: 2026-11-03
Updated: 2026-11-06
Project page: https://zhangdaxia22.github.io/AceAction-5M
Terminology
Sources
- SIMA 2: A Generalist Embodied Agent for Virtual Worlds
- EgoCS-400K: An Egocentric Gameplay Dataset for World Models
- MineRL: A Large-Scale Dataset of Minecraft Demonstrations
- DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
- WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG
- Scaling Instructable Agents Across Many Simulated Worlds
- GameHorizon Suite: Multi-Horizon Data and Evaluation in Gameplay
- Scaling Behavior Cloning Improves Causal Reasoning: An Open Model for Real-Time Video Game Playing
- 3A-VLA: Abstraction-Aligned Action Learning for Vision-Language Agents in 3D Game Worlds
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents