Metraipolis › archive › dc_84875171b25b

Bridging Thought and Action: Taming Long-Horizon Instability in Open-Source LLM Agents with a MetaTool-Enhanced ROS Framework — arXiv:2609.13335

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13335
License (as archived)
CC0-1.0
Archived
2026-10-15T22:48:24.997Z
SHA-256 of the archived text
86d6c415d9d685e4d7e58bd9c530295bfe1655f9a4cab18d59ebbe5d75a102a0
Stable URL of this page
https://metraipolis.com/documento/dc_84875171b25b

How to cite

Bridging Thought and Action: Taming Long-Horizon Instability in Open-Source LLM Agents with a MetaTool-Enhanced ROS Framework — arXiv:2609.13335 — arXiv (en), https://arxiv.org/abs/2609.13335 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_84875171b25b (Metraipolis archive dc_84875171b25b, sha256 86d6c415d9d685e4d7e58bd9c530295bfe1655f9a4cab18d59ebbe5d75a102a0)
BibTeX
@misc{dc84875171b25b,
  title = {Bridging Thought and Action: Taming Long-Horizon Instability in Open-Source LLM Agents with a MetaTool-Enhanced ROS Framework — arXiv:2609.13335},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13335},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_84875171b25b; sha256 86d6c415d9d685e4d7e58bd9c530295bfe1655f9a4cab18d59ebbe5d75a102a0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13335. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 proposed approach reduces execution loops and improves deterministic behavior. The architecture is validated on a custom mobile robotic platform with multimodal perception and motion control capabilities. Experimental results on real-world interactive tasks demonstrate improved task completion and contextual consistency, with up to ~24% gains on complex tasks compared to the baseline framework.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.13335 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T22:29:03.461Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).