{
  "id": 5092,
  "url": "https://arxiv.org/abs/2605.01147v1",
  "title": "Position: Safety and Fairness in Agentic AI Depend on Interaction Topology, Not on Model Scale or Alignment",
  "summary": "As large language models are increasingly deployed as interacting agents in high-stakes decisions, the AI safety community assumes that safety properties of individual models will compose into safe multi-agent behavior. This position paper argues that this assumption is fundamentally mistaken. In agentic AI, safety is determined by interaction topology, not model weights. When agents deliberate sequentially or aggregate via parallel voting with a judge, the structure of information flow and deci",
  "authors": "Tanav Singh Bajaj, Nikhil Singh, Karan Anand, Eishkaran Singh",
  "category": "research",
  "topics": "bias-fairness,safety-alignment,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-05-01T22:49:10.000Z",
  "fetched_at": "2026-07-14T16:31:31.210Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/5092",
  "original_url": "https://arxiv.org/abs/2605.01147v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}