{
  "id": 12335,
  "url": "https://arxiv.org/abs/2607.19190v1",
  "title": "Agentic Real2Sim: Physics-based World Modeling with Vision-Language Agents",
  "summary": "Real-to-sim conversion for robotic interaction with objects remains labor-intensive because it requires more than visual reconstruction: a streamlined real2sim process must recover scene geometries and object states, infer physical parameters, and assemble actors, objects, cameras, poses, and trajectories into a runnable physical simulation. Today this process still depends on manual tuning of visual foundation models, mesh cleanup, coordinate-frame alignment, and brittle workflow glue across vi",
  "authors": "Guanxiong Chen, Qianjun Xia, Jiawei Peng, Heng Zhang, Bole Ma, Justin Qian et al.",
  "category": "research",
  "topics": "safety-alignment,jobs-economy,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-21T15:23:38.000Z",
  "fetched_at": "2026-07-22T05:10:49.469Z",
  "source_slug": "arxiv-ethics",
  "source_name": "arXiv",
  "source_homepage": "https://arxiv.org",
  "ethics_ai_record_url": "https://ethics.ai/record/12335",
  "original_url": "https://arxiv.org/abs/2607.19190v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}