Embodied Turing Machines: Stateful Code for Robot Recursive Self-Improvement

arXiv:2610.12369 · cs.RO, cs.CV · Submitted 2026-10-08 · Read on arXiv

cs.RO, cs.CV

Submitted: 2026-10-08

Updated: 2026-10-08

Code: https://github.com/Awomo-WestlakeDI/Awomo-0.5

Project page: https://mmlab.hk/research/PhysicalRSI

Terminology

• Agent Harness — 37× in this paper · explained in 2 episodes
• Generalization — 30× in this paper · explained in 13 episodes
• Benchmark — 17× in this paper · explained in 2 episodes
• Agent-as-Policy — 14× in this paper · explained in 1 episode
• World Action Model — 7× in this paper
• Fine-Tuning — 6× in this paper · explained in 5 episodes
• Core — 4× in this paper · explained in 2 episodes
• Foundation Model — 4× in this paper · explained in 3 episodes
• In Conference on Robot Learning — 4× in this paper
• Benchmarking — 3× in this paper · explained in 4 episodes
• Foundation Models — 3× in this paper · explained in 7 episodes
• Trace — 3× in this paper · explained in 2 episodes
• Affordance — 2× in this paper · explained in 1 episode
• In International Conference on Machine Learning — 2× in this paper
• Abstraction — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Action Flow — 1× in this paper · explained in 1 episode
• Action Space — 1× in this paper · explained in 1 episode
• Alignment — 1× in this paper · explained in 1 episode
• Breadth-First Search — 1× in this paper
• Compositional Generalization — 1× in this paper · explained in 4 episodes
• Grounding — 1× in this paper · explained in 3 episodes
• In International Conference on Learning Representations — 1× in this paper
• International Conference on Robotics and Automation — 1× in this paper
• Steering — 1× in this paper · explained in 2 episodes
• VLA Models — 1× in this paper · explained in 3 episodes
• Verification — 1× in this paper · explained in 2 episodes
• Vision-Language Model (VLM) — 1× in this paper · explained in 3 episodes
• World Action Model (WAM) — 1× in this paper · explained in 3 episodes

Sources

• RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies
• Show-Harness: Just a VLM Agent Can Play Robots
• RHO: Your Coding Agent is Secretly a Roboticist
• ME-Brain-1.0: Memory, Cognition and Action for Evolving Embodied Intelligence
• RLDX-1 Technical Report
• G0.5: One Autoregressive Stream for Robot Reasoning and Action
• ASPIRE: Agentic /Skills Discovery for Robotics
• InternVLA-A1.5: Unifying Understanding, Latent Foresight, and Action for Compositional Generalization
• InternW0-: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data
• EmbodiedSWE: Coding Agents for Long Horizon Dexterous Robotics
• StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developing
• A Pragmatic VLA Foundation Model
• Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectories
• Beyond Data Scaling: Representation-Centric Continued Pre-training for Vision-Language-Action Models
• Route by Kinematics, Act by Observation: Kinematics-Supervised Expert Routing in MoE-Augmented VLA
• SimpleMemVLA: A Simple but Effective Native-Video Memory for Vision-Language-Action Models
• Harness VLA: Steering Frozen VLAs into Reliable Manipulation Primitives via Memory-Guided Agents
• An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond

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
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies
• Fine-tuning is Not Enough: A Parallel Framework for Collaborative Imitation and Reinforcement Learning in End-to-end Autonomous Driving