{
  "id": 17342,
  "url": "https://arxiv.org/abs/2608.06161v1",
  "title": "iARCS: Iterative Agentic RL for Controllable 3D Scene Generation",
  "summary": "Synthetic 3D scene generation is increasingly used as a data source for computer vision and embodied AI, but existing generators often optimize perceptual realism without reliably satisfying task-critical functional constraints. This mismatch limits the usefulness of synthetic data for downstream training, where accessibility, traversability, and spatial rule compliance are often essential. We present iARCS, an iterative agentic reinforcement learning framework that adapts a pretrained scene gen",
  "authors": "Saugat Adhikari, Ashok Prasad Neupane, Pramish Paudel, Ajad Chhatkuli, Danda Pani Paudel",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-08-06T15:30:21.000Z",
  "fetched_at": "2026-08-07T05:10:58.501Z",
  "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/17342",
  "original_url": "https://arxiv.org/abs/2608.06161v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}