{
  "id": 19161,
  "url": "https://arxiv.org/abs/2608.13456v1",
  "title": "A Unifying Perspective on Causal World Models: From Observations to Representations to Structure",
  "summary": "World Models (WM) are increasingly seen as a foundation for intelligent agents that can predict, plan, and act beyond their training distribution. In this paper, we study WMs from a causal perspective across multiple levels of abstraction, ranging from perceptual observations to building a conceptual representation of the structure governing the environment dynamics. We argue that useful WMs must go beyond generative capabilities alone: they should also capture entity properties, entity-to-entit",
  "authors": "Avinash Kori, Fabrizio Russo",
  "category": "research",
  "topics": "agents-autonomy,environment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-13T16:40:35.000Z",
  "fetched_at": "2026-08-14T05:10:49.168Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/19161",
  "original_url": "https://arxiv.org/abs/2608.13456v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}