iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary Domains

Title:iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary Domains

Abstract:Agentic AI based on Large Language Model generalization capabilities offers a wide range of potential applications, including planning for embodied tasks. For example, embodied agents based on Foundation models can generate plausible plans in autonomous robotics scenarios. Due to limited context windows or hallucinatory phenomena in the next-token prediction formulation, behaviors may be generated without establishing whether the deployed robot and the observed environment actually support the requested operation, in what we call a "grounding failure". Thanks to the recent improvements in reasoning capabilities of foundation models, autonomous robot behavior generation problem can be formulated as a code generation problem. We present this http URL, a Markdown standard and generation framework, that allows anchoring this process in complementary forms of deployment evidence. Through open-vocabulary semantic mapping, we combine local vision-language detections and object segmentation and refer them to persistent object records in this intermediate standardized representation, allowing agentic introspection. We then study this new technique on a simulated TIAGo, on navigation-and-manipulation tasks, showing how this standardized representation jointly supports skill self-assessment and executable task generalization.

7 pages, 2 figures, 1 table. Accepted at the 13th Italian Workshop on Artificial Intelligence and Robotics (AIRO 2026). Project page: this https URL

Robotics (cs.RO); Artificial Intelligence (cs.AI)

arXiv:2610.10962 [cs.RO]

(or arXiv:2610.10962v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2610.10962 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.