LATIDIA · Robótica

Bridging Thought and Action: Doming Long-Horizon Intability in Open-Source LLM Agents with a MetaTool-Enhanced ROS Framework

arXiv: 2609.13335v1Tipo de anuncio: nuevo Resumen: los modelos de lenguaje grandes (LLM) han permitido una interacción humano-robot más natural, pero los modelos de código abierto a menudo exhiben un razonamiento inestable a largo plazo y una acción ineficiente

La noticia

arXiv:2609.13335v1 Announce Type: new Abstract: Large Language Models (LLMs) have enabled more natural human-robot interaction, but open-source models often exhibit unstable long-horizon reasoning and inefficient action execution when deployed in agentic robotic frameworks. This paper presents an enhanced ROS-Agent based architecture that improves task reliability and execution efficiency for agentic robotic systems using open-source LLMs. The proposed system introduces a novel intermediate mechanism, termed the MetaTool, which enforces structured planning prior to action execution. Given a natural-language command, the MetaTool induces the LLM to generate a pseudo-code plan of intended tool invocations, which is stored in the ROS-Agent's scratchpad and persists throughout execution. By explicitly separating planning from execution, the