Skip to content

Author

Mahantesh Halapannavar

We have 1 of 1 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.

Review Aug 2026

Agentic Harnesses: LLM-Driven Verification Layers for Robot Autonomy

This work proposes a LLM-driven verification layer between planning and execution to evaluate action permissibility, and achieves near 85% precision across accept/escalate/reject categories, with negligible errors between accepting and rejecting tasks, and errors mostly manifesting at the escalate boundary.

Rohan Bhagra, Mahantesh Halapannavar, Uddhav Bhattarai · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.