VLMs are Native Action Models: Unleashing the Manipulation Capabilities of VLMs with Explicit Action-Space Grounding

arXiv:2610.12832 · cs.RO · Submitted 2026-10-09 · Read on arXiv

cs.RO

Submitted: 2026-10-09

Updated: 2026-10-09

Comments: 30 pages, 13 figures. Project page: https://general-robo.github.io/EASG/

Code: https://github.com/General-Robo/EASG

Project page: https://general-robo.github.io/EASG

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Grounding — 1× in this paper · explained in 3 episodes

Sources

• RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation
• RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
• CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation
• LoRA: Low-Rank Adaptation of Large Language Models
• VIA: Visual Interface Agent for Robot Control
• Do You Know Where Your Camera Is? View-Invariant Policy Learning with Camera Conditioning
• DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
• Evaluating Real-World Robot Manipulation Policies in Simulation
• Code as Policies: Language Model Programs for Embodied Control
• Flow Matching for Generative Modeling
• ASPIRE: Agentic /Skills Discovery for Robotics
• GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
• On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability
• SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model
• RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulation
• ENPIRE: Agentic Robot Policy Self-Improvement in the Real World
• Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V
• World Action Models are Zero-shot Policies
• Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
• Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy

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