Author

Yao-Yuan Yan

h-index 1 View on Semantic Scholar

We have 3 of 7 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Sep 2026

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

Long-horizon robot execution requires a clear distinction between a model's proposal, a controller's termination, and verified task completion. We present RegenHarness, an evidence-gated robot-agent harness connecting task planning to heterogeneous robot skills. Its execution architecture couples a model loop for conte...

Kai-Lin Wang, Hao-Xiang Jie, Yao-Yuan Yan et al. · 1 citation

Preprint Sep 2026

Harness Robotic OS: A Unified Embodied-Agent Runtime for Closed-Loop Quadruped Inspection

These results validate the deployed navigation and inspection closed loop, while HROS provides an extensible software foundation for memory-augmented, voice-aware, and continuously improvable embodied inspection agents.

Yao-Yuan Yan, Zhi-You Heng, Hao-Xiang Jie et al. · 1 citation · ⚡1

Preprint Aug 2026

Ontology-Grounded World Models for Failure Diagnosis and Closed-Loop Repair in Physical AI Systems

Onto-EV-WM is presented, an ontology-grounded diagnosis and verification-gated correction interface layered above EV-WM rather than a replacement world-model architecture, an ontology-grounded diagnosis and verification-gated correction interface layered above EV-WM.

Kai-Lin Wang, Hao-Xiang Jie, Yao-Yuan Yan et al. · 1 citation