Metraipolis › archive › dc_2f51ddd31dbc

Design and Evaluation of LLM Chaining-Based Task Planning for General Purpose Service Robots — arXiv:2609.29043

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.29043
License (as archived)
CC0-1.0
Archived
2026-10-08T04:27:14.013Z
SHA-256 of the archived text
f0118baf6fc717599b873a3510ccc07f80692701d3d5744054e9c3272b7a5ad1
Stable URL of this page
https://metraipolis.com/documento/dc_2f51ddd31dbc

How to cite

Design and Evaluation of LLM Chaining-Based Task Planning for General Purpose Service Robots — arXiv:2609.29043 — arXiv (en), https://arxiv.org/abs/2609.29043 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2f51ddd31dbc (Metraipolis archive dc_2f51ddd31dbc, sha256 f0118baf6fc717599b873a3510ccc07f80692701d3d5744054e9c3272b7a5ad1)
BibTeX
@misc{dc2f51ddd31dbc,
  title = {Design and Evaluation of LLM Chaining-Based Task Planning for General Purpose Service Robots — arXiv:2609.29043},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.29043},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2f51ddd31dbc; sha256 f0118baf6fc717599b873a3510ccc07f80692701d3d5744054e9c3272b7a5ad1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.29043. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

General Purpose Service Robot (GPSR) tasks, as defined in the RoboCup@Home benchmark, require robots to interpret diverse natural language commands and generate multi-step action sequences in real home environments. Conventional Single Prompt (SP) approaches suffer from context bloat and the "Lost in the Middle" phenomenon, leading to unreliable task planning. We propose an LLM chaining architecture that separates instruction classification and action generation into two specialized stages, reducing per-inference prompt length by approximately 45% while improving planning consistency. We evaluate our method using 100 randomly generated GPSR commands across three language models spanning local open-source and frontier cloud deployment contexts. Results show consistent planning improvements over SP across all models, with gains of up to +37 percentage points on local models. Further, real-robot execution experiments on the Toyota Human Support Robot (HSR) reveal that planning success alone does not guarantee task completion, with 6 of 10 tasks completing successfully and execution-layer failures identified as the primary remaining bottleneck.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.29043 — 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 2026-10-08T03:50:57.987Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).