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 iAm.md, 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.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Guarino, V., Musumeci, E., Suriani, V., & Nardi, D. (2026). iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary Domains. https://omanscience.com/en/articles/iam-md-robot-skill-self-assessment-through-agentic-introspection-for-unknown-open-vocabulary-domains
MLA 9
Guarino, Vincenzo, et al. "iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary Domains." https://omanscience.com/en/articles/iam-md-robot-skill-self-assessment-through-agentic-introspection-for-unknown-open-vocabulary-domains.
Chicago (author–date)
Guarino, Vincenzo, Emanuele Musumeci, Vincenzo Suriani, and Daniele Nardi. 2026. "iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary Domains." https://omanscience.com/en/articles/iam-md-robot-skill-self-assessment-through-agentic-introspection-for-unknown-open-vocabulary-domains.
Harvard
Guarino, V., Musumeci, E., Suriani, V. and Nardi, D. (2026) 'iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary Domains', Available at: https://omanscience.com/en/articles/iam-md-robot-skill-self-assessment-through-agentic-introspection-for-unknown-open-vocabulary-domains.
Vancouver
Guarino V, Musumeci E, Suriani V, Nardi D. iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary Domains. https://omanscience.com/en/articles/iam-md-robot-skill-self-assessment-through-agentic-introspection-for-unknown-open-vocabulary-domains
IEEE
V. Guarino, E. Musumeci, V. Suriani, and D. Nardi, "iAm.md: Robot Skill Self-Assessment through Agentic Introspection for Unknown Open-Vocabulary Domains," https://omanscience.com/en/articles/iam-md-robot-skill-self-assessment-through-agentic-introspection-for-unknown-open-vocabulary-domains.