Inloggen
inzicht - Corrective Action Planning with Large Language Models
CAPE: Corrective Actions from Precondition Errors using Large Language Models
The author proposes CAPE, a novel approach that leverages few-shot reasoning from action preconditions to generate corrective actions and improve plan quality. By injecting contextual information in the form of precondition errors, CAPE substantially enhances the executability and correctness of plans generated by LLMs.
CAPE: Corrective Actions from Precondition Errors using Large Language Models
提案されたCAPEアプローチは、前提条件エラーを解決するための修正アクションを生成し、実行可能な計画の品質と正確性を向上させることができます。
Producten | Bronnen
© 2024 by Linnk AI