HarnessPAI: An Evolving Harness for Physical AI
cs.RO, cs.AI
Submitted: 2026-09-24
Updated: 2026-09-24
Code: https://github.com/mmints/vacusim
Project page: https://darwin-agent.github.io/HarnessPAI
Terminology
Sources
- $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
- WorldVLA: Towards Autoregressive Action World Model
- GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation
- $\pi_\texttt{RL}$: Online RL Fine-tuning for Flow-based Vision-Language-Action Models
- HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
- Show-Harness: Just a VLM Agent Can Play Robots
- ETA: A New Agentic Paradigm for Embodied Tasks
- TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimization
- HarnessWAM: Bridging Prediction and Deliberation in World Action Models
- NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Tasks
- $\pi^{*}_{0.6}$: a VLA That Learns From Experience
- $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
- FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models
- MolmoAct: Action Reasoning Models that can Reason in Space
- RoboHarness: A Memory-Augmented Policy Harness for Vision-Language-Action Model Robustness via In-Context Adaptation
- Mi-Memory: A Lifecycle Memory Framework for Personal AI
- PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution
- VLA-RL: Towards Masterful and General Robotic Manipulation with Scalable Reinforcement Learning
- ASPIRE: Agentic /Skills Discovery for Robotics
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