{
  "id": 4384,
  "url": "https://arxiv.org/abs/2605.13579v1",
  "title": "Position: Assistive Agents Need Accessibility Alignment",
  "summary": "Assistive agents for Blind and Visually Impaired (BVI) users require accessibility alignment as a first-class design objective. Despite rapid progress in agentic AI, most systems are designed and evaluated under assumptions of sighted interaction, low-cost verification, and tolerable trial-and-error, leading to systematic failures in assistive scenarios that cannot be resolved by model scaling or post-hoc interface adaptations alone. Drawing on an analysis of 778 assistance task instances from p",
  "authors": "Jie Hu, Changyuan Yan, Yu Zheng, Ziqian Wang, Jiaming Zhang",
  "category": "research",
  "topics": "safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-13T14:13:53.000Z",
  "fetched_at": "2026-07-14T16:30:59.235Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/4384",
  "original_url": "https://arxiv.org/abs/2605.13579v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}