{
  "id": 14814,
  "url": "https://arxiv.org/abs/2607.26935v1",
  "title": "What Does It Take to Detect an AI Agent? Minimal Feature Sets for Behavioral Detection under Browser Automation",
  "summary": "Bot detectors deployed at scale treat traffic as binary: human or bot. This assumption breaks when AI agents browse the web through browser automation, a traffic class that is neither and that binary classifiers structurally cannot represent. We present a three-class detection framework distinguishing humans, bots, and AI agents, and show that the binary-vs-agent confusion is architectural: a binary human-vs-bot detector misroutes agent sessions because its label space lacks an agent class. On o",
  "authors": "Vishisht Choudhary, Lukas Schmidt, Anne Zoë Kenntner, Feras Skhab, Michel Osswald, Jens Ernstberger",
  "category": "research",
  "topics": "jobs-economy,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-29T14:05:26.000Z",
  "fetched_at": "2026-07-30T05:10:24.387Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/14814",
  "original_url": "https://arxiv.org/abs/2607.26935v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}