{
  "id": 10975,
  "url": "https://arxiv.org/abs/2607.14447",
  "title": "Do Generative AI Assistants Respect robots.txt? Tracing Web Access Beyond Visible Answers",
  "summary": "arXiv:2607.14447v1 Announce Type: new Abstract: AI assistants increasingly retrieve web content at inference time to provide fresh and grounded answers, yet it remains unclear whether these search-augmented capabilities respect website-owner restrictions expressed through robots.txt. We present a controlled empirical study of ten widely used AI assistants with advertised web-search capabilities. For each assistant, we first identify a configuration that actually produces observable web-browsing ",
  "authors": "Gabriel Lopez-Fonseca, David Rodriguez, Stefan Bechtold, Jose M. Del Alamo",
  "category": "research",
  "topics": "agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-17T04:00:00.000Z",
  "fetched_at": "2026-07-17T05:10:53.887Z",
  "source_slug": "arxiv-cscy",
  "source_name": "arXiv cs.CY",
  "source_homepage": "https://arxiv.org/list/cs.CY/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/10975",
  "original_url": "https://arxiv.org/abs/2607.14447",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}