How Many Exposures Does a World Model Need? Learning Unseen Game Mechanics at Test Time
cs.LG, cs.AI, cs.CV
Submitted: 2026-11-09
Updated: 2026-11-09
Code: https://github.com/DriesSmit/ARC3-
Terminology
Sources
- The Surprising Effectiveness of Test-Time Training for Few-Shot Learning
- ARC-AGI-3: A New Challenge for Frontier Agentic Intelligence
- Sensi: Learn One Thing at a Time -- Curriculum-Based Test-Time Learning for LLM Game Agents
- V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning
- DiG-bench: Discovery in Games
- Genie: Generative Interactive Environments
- Exploration by Random Network Distillation
- On the Measure of Intelligence
- ARC Prize 2025: Technical Report
- OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3
- One-shot World Models Using a Transformer Trained on a Synthetic Prior
- PRO-LONG: Programmatic Memory Enables Long-Horizon Reasoning
- NVIDIA-labs OO Agents: Native Python Object-Oriented Agents
- NovPhy: A Testbed for Physical Reasoning in Open-world Environments
- Slots, Transitions, Loops: Learning Composable World Models for ARC
- World Models
- Hallucination in World Models is Predictable and Preventable
- Learning Massively Multitask World Models for Continuous Control
- Matrix-game 2.0: An open-source, real-time, and streaming interactive world model
- AXIOM: Learning to Play Games in Minutes with Expanding Object-Centric Models
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis