Metraipolis › archive › dc_aa4107972cd1

CT-SAFR: Safe and Interpretable Chain-of-Thought Reasoning for Autonomous Robots: A Multi-Layered Verification Framework for Trustworthy AI-Driven Robotic Decision Making — arXiv:2609.09692

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.09692
License (as archived)
CC0-1.0
Archived
2026-10-16T07:26:08.359Z
SHA-256 of the archived text
e1331d3bfd5bba5fa5b794a7ce13948cdc877180845b2aaeaa967a3742f57875
Stable URL of this page
https://metraipolis.com/documento/dc_aa4107972cd1

How to cite

CT-SAFR: Safe and Interpretable Chain-of-Thought Reasoning for Autonomous Robots: A Multi-Layered Verification Framework for Trustworthy AI-Driven Robotic Decision Making — arXiv:2609.09692 — arXiv (en), https://arxiv.org/abs/2609.09692 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aa4107972cd1 (Metraipolis archive dc_aa4107972cd1, sha256 e1331d3bfd5bba5fa5b794a7ce13948cdc877180845b2aaeaa967a3742f57875)
BibTeX
@misc{dcaa4107972cd1,
  title = {CT-SAFR: Safe and Interpretable Chain-of-Thought Reasoning for Autonomous Robots: A Multi-Layered Verification Framework for Trustworthy AI-Driven Robotic Decision Making — arXiv:2609.09692},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09692},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aa4107972cd1; sha256 e1331d3bfd5bba5fa5b794a7ce13948cdc877180845b2aaeaa967a3742f57875},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09692. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Chain-of-Thought (CoT) prompting enables LLMs to perform explicit, step-by-step reasoning, creating opportunities for sophisticated autonomous robots. However, recent research reveals that reasoning models verbalize their actual decision processes only 25-39% of the time, with faithfulness degrading 44% on complex tasks. This paper presents CT-SAFR (Chain-of-Thought Safety and Faithfulness for Robotics), a multi-layered verification framework achieving 94.2% hallucination detection (n = 500, 95% CI: 91.8-95.9%) with sub-500ms latency. Through a warehouse robot case study, this work demonstrates 87% reduction in unsafe reasoning outputs (p < 0.001) and provides recommendations for responsible deployment of reasoning-capable autonomous robots.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-10 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.09692 — 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 2026-10-16T07:00:16.340Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).