DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents

arXiv:2609.40306 · cs.RO, cs.AI, cs.LG · Submitted 2026-09-30 · Read on arXiv

cs.RO, cs.AI, cs.LG

Submitted: 2026-09-30

Updated: 2026-09-30

Code: https://github.com/PhyAgentOS/PhyAgentOS

Project page: https://denghaoyuan123.github.io/Dynaharness_page

Terminology

• Benchmark — 25× in this paper · explained in 2 episodes
• Verifier — 20× in this paper · explained in 2 episodes
• Trace — 18× in this paper · explained in 2 episodes
• Ablation — 16× in this paper · explained in 1 episode
• Grounding — 15× in this paper · explained in 3 episodes
• Post-Selection — 10× in this paper · explained in 2 episodes
• Verification — 9× in this paper · explained in 2 episodes
• Adaptation — 5× in this paper · explained in 1 episode
• Reinforcement Learning — 3× in this paper · explained in 4 episodes
• Generalization — 2× in this paper · explained in 13 episodes
• Generative AI — 2× in this paper · explained in 2 episodes
• Provenance — 2× in this paper · explained in 3 episodes
• Steering — 2× in this paper · explained in 2 episodes
• Action Space — 1× in this paper · explained in 1 episode
• Additive Decomposition — 1× in this paper · explained in 1 episode
• Admissibility — 1× in this paper · explained in 2 episodes
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes
• Vision-Language-Action (VLA) Models — 1× in this paper · explained in 2 episodes

Sources

• GaP: A Graph-as-Policy Multi-Agent Self-Learning Harness For Variational Automation Tasks
• Show-Harness: Just a VLM Agent Can Play Robots
• ETA: A New Agentic Paradigm for Embodied Tasks
• UniIntervene: Agentic Intervention for Efficient Real-World Reinforcement Learning
• RHO: Your Coding Agent is Secretly a Roboticist
• LIBERO-Plus: In-depth Robustness Analysis of Vision-Language-Action Models
• CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation
• Addressing the Orchestration Gap in Generalist Robots via Physical Agency
• Sequential Planning via Anchored Robotic Keypoints
• HarnessWAM: Bridging Prediction and Deliberation in World Action Models
• RoboEXP: Action-Conditioned Scene Graph via Interactive Exploration for Robotic Manipulation
• HARBOR: A Harness Framework for Agentic Robot Reinforcement Learning
• VLS: Steering Pretrained Robot Policies via Vision-Language Models
• PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution
• ASPIRE: Agentic /Skills Discovery for Robotics
• Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• InSight: Self-Guided Skill Acquisition via Steerable VLAs
• Towards the Harness of Embodied Agents

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