D-World: An Explicit World-Language-Action Model with Recursive Self-Improvement under Dual Control
cs.RO, cs.AI
Submitted: 2026-10-12
Updated: 2026-10-12
Comments: 23 pages, 4 figures, 2 tables
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond
- Systematically Exploring the Capabilities of GPT-6 Astra as Embodied Policies
- RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
- World Action Models are Zero-shot Policies
- World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis
- Video2World: Benchmarking Coding Agents for Interactive World Modeling from Embodied Videos
- BVB: Benchmarking Agentic Video Understanding via Programmatic Reconstruction in Blender
- GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
- Fast-WAM: Do World Action Models Need Test-time Future Imagination?
- Building Explicit World Model for Zero-Shot Open-World Object Manipulation
- Code World Model: Coding Agent as World Brain
- VisualPatchWorld: Code World Models as Latent Structured Representations for Planning
- SimEX: Simulation-Integrated Robotics AutoResearch
- Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents
- Agentic RSR: Real-to-Sim-to-Real through Scene Reconstruction and Execution-Grounded Robot Policies
- OpenRUA: Robot-Use Agents Are Zero-Shot Visuomotor Policies
- Generalizing Manipulation Skills with a Local Coding Agent
Related papers
- FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
- MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
- RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
- ARC: A Reasoning Recipe for Robot Foundation Models
- HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
- APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies