Embodied AI is a crucial frontier in robotics, capable of planning and executing action sequences for robots to accomplish long-horizon tasks in physical environments.

Warning: this paper contains example data that may be offensive or harmful.

Humans write code in a fundamentally interactive manner and rely on constant execution feedback to correct errors, resolve ambiguities, and decompose tasks.

Ta s k: Your task is to boil tin.

Recently, large language models (LLMs) ( e.g., GPT -3 and ChatGPT) have shown remarkable zero-shot and few-shot performance on various tasks [

Existing methods on visual knowledge extraction often rely on the predefined format (e.g., sub-verb-obj tuples) or vocabulary (e.g., relation types), restricting the expressiveness of the extracted knowledge. In this work, we take a first exploration to a new paradigm of open visual knowledge extraction.

Systematic literature reviews (SLRs) play an essential role in summarising, synthe-sising and validating scientific evidence.