RegenHarness: A Robot Agent Harness with Evidence-Gated Recursive Self-Improvement

arXiv:2609.27612 · cs.RO · Submitted 2026-09-23 · Read on arXiv

cs.RO

Submitted: 2026-09-23

Updated: 2026-09-23

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

Terminology

• Verification — 29× in this paper · explained in 2 episodes
• Verifier — 14× in this paper · explained in 2 episodes
• Agent Harness — 9× in this paper · explained in 1 episode
• Provenance — 5× in this paper · explained in 3 episodes
• Trace — 5× in this paper · explained in 2 episodes
• World Model — 5× in this paper · explained in 7 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Affordance — 2× in this paper · explained in 1 episode
• Generalization — 2× in this paper · explained in 13 episodes
• Grounding — 2× in this paper · explained in 3 episodes
• Task Planning — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Accuracy — 1× in this paper · explained in 1 episode
• Action Space — 1× in this paper · explained in 1 episode
• Adaptation — 1× in this paper · explained in 1 episode
• Admissibility — 1× in this paper · explained in 2 episodes
• Agentic AI — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Decode — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Ontology — 1× in this paper · explained in 2 episodes
• Resource Constraints — 1× in this paper · explained in 3 episodes
• Unified Framework — 1× in this paper · explained in 5 episodes

Sources

• MAGMA-GEN: Validated Recovery Supervision from Ambiguous Failures via Counterfactual Re-Execution
• $\pi_0$: A Vision-Language-Action Flow Model for General Robot Control
• RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control
• From Model Scaling to System Scaling: Scaling the Harness in Agentic AI
• ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation
• Harness Engineering for Physical AI: Robot Middleware Is the Harness Layer
• LIBERO-RECOVER: Beyond Task Success Towards Failure Recovery in Robotic Manipulation Models
• PhyAgentOS: A Self-Evolving Operating System for Embodied Agents with Decoupled Cognitive Planning and Physical Execution
• Code as Agent Harness
• $\pi_{0.5}$: a Vision-Language-Action Model with Open-World Generalization
• EV-WM: Event-Verified World Models for Long-Horizon Robotic Manipulation
• EmbodiedSkills: World Action Model-augmented Cascaded Skills for Vision-Language-Action Agent
• Self-Harness: Harnesses That Improve Themselves
• CommitFlow: Semantic Commitment Verification and Local Correction for Long-Horizon Robot Manipulation VLA Execution
• HoloAgent-0: A Unified Embodied Agent Framework with 3D Spatial Memory

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