Metraipolis › archive › dc_5ebb7e38d49f

MistyPilot: Enabling Social-Robot Control through Multi-Agent LLM Skill Orchestration — arXiv:2608.15549

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15549
License (as archived)
CC0-1.0
Archived
2026-10-18T18:03:39.732Z
SHA-256 of the archived text
64eb86d6b5947de635f877699b8f9829534938accec6658d6e526c97110aeb20
Stable URL of this page
https://metraipolis.com/documento/dc_5ebb7e38d49f

How to cite

MistyPilot: Enabling Social-Robot Control through Multi-Agent LLM Skill Orchestration — arXiv:2608.15549 — arXiv (en), https://arxiv.org/abs/2608.15549 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5ebb7e38d49f (Metraipolis archive dc_5ebb7e38d49f, sha256 64eb86d6b5947de635f877699b8f9829534938accec6658d6e526c97110aeb20)
BibTeX
@misc{dc5ebb7e38d49f,
  title = {MistyPilot: Enabling Social-Robot Control through Multi-Agent LLM Skill Orchestration — arXiv:2608.15549},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15549},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5ebb7e38d49f; sha256 64eb86d6b5947de635f877699b8f9829534938accec6658d6e526c97110aeb20},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15549. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Programming small social robots from natural-language instructions requires more than invoking isolated APIs. Interactive tasks combine reactive physical behaviors with stateful social behaviors, while existing interfaces often require developers to manually compose APIs into skills, configure their parameters, bind sensor events to skills, and manage task states at runtime. We present MistyPilot, a multi-agent LLM framework that interprets high-level natural-language instructions and orchestrates the corresponding skills on the Misty social robot. A Task Router dispatches each instruction to one of two specialized agents: a Physically Interactive Agent for sensor-triggered robot control and direct skill invocation, and a Social Interaction Agent for dialogue-oriented task-state management and context-dependent multimodal response generation. To improve efficiency, the Social Interaction Agent reuses previously generated results when applicable and invokes full generation otherwise. We evaluate MistyPilot on five component-level suites, with sensor bindings and skill invocations executed on the physical Misty robot, and a preliminary user study with 12 participants. MistyPilot attains high accuracy on routing, sensor-skill binding, task-state parsing, result reuse, and skill extension up to 100 skills, and lower variance than an otherwise identical single-agent baseline, while participants report positive perceptions of usability and interaction quality. The code will be made publicly available via the project page.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.15549 — 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 2026-10-18T16:29:14.025Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).