{
  "id": 210,
  "url": "https://arxiv.org/abs/2607.04681v1",
  "title": "Do Vision-Language-Action Models Mean What They Say? On the Role of Faithfulness in Embodied Reasoning",
  "summary": "Embodied Chain-of-Thought has emerged as a promising mechanism to enhance robot decision-making and interpretability in black-box Vision-Language Action (VLA) models. However, whether this verbalized Chain-of-Thought truthfully reflects the policy's underlying decision process remains poorly understood. We distinguish between functional reasoning, in which reasoning improves task performance, and faithful reasoning, in which reasoning truly reflects the policy's internal decision process. We arg",
  "authors": "Matthew Foutter, Matteo Cercola, Lena Wild, Yunshan Wang, Michelle Li, Daniele Gammelli et al.",
  "category": "research",
  "topics": "regulation,safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-06T05:10:27.000Z",
  "fetched_at": "2026-07-14T14:14:24.245Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/210",
  "original_url": "https://arxiv.org/abs/2607.04681v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}