Metraipolis › archive › dc_5bebe77e6e4d

WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents — arXiv:2609.40325

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.40325
License (as archived)
CC0-1.0
Archived
2026-10-07T12:43:11.231Z
SHA-256 of the archived text
dd33e7a6bc5f380aa2753d4af3026addd003ec4b4f3a018c9f7006c28404297d
Stable URL of this page
https://metraipolis.com/documento/dc_5bebe77e6e4d

How to cite

WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents — arXiv:2609.40325 — arXiv (en), https://arxiv.org/abs/2609.40325 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5bebe77e6e4d (Metraipolis archive dc_5bebe77e6e4d, sha256 dd33e7a6bc5f380aa2753d4af3026addd003ec4b4f3a018c9f7006c28404297d)
BibTeX
@misc{dc5bebe77e6e4d,
  title = {WorldAuditBench: Interactive 3D World Auditing with Multimodal Agents — arXiv:2609.40325},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.40325},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5bebe77e6e4d; sha256 dd33e7a6bc5f380aa2753d4af3026addd003ec4b4f3a018c9f7006c28404297d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.40325. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As interactive 3D worlds are increasingly used to study intelligent behavior, it becomes important to develop efficient pipelines for identifying anomalies in these simulated environments, such as floating objects, traversable walls, or objects inconsistent with the surrounding scene. Multimodal AI systems, including vision-language models (VLMs) and vision-language-action models (VLAs), have shown potential for automating this task. However, 3D world auditing is complex, requiring the close coupling of two distinct capabilities: action, to navigate the 3D world and search for anomalies systematically and efficiently; and visual reasoning, to understand the environment and identify anomalies from multimodal observations. It remains largely unexplored whether multimodal agents can effectively couple these two capabilities, using visual reasoning to identify potential anomalies while taking actions to validate them. In this paper, we introduce WorldAuditBench, a benchmark for 3D world auditing comprising 213 anomaly tasks across 13 environments built with Unreal Engine 5 and this http URL , spanning five anomaly families. We evaluate five frontier models under a fixed exploration budget using two auditing paradigms: VLA-based exploration followed by VLM-based anomaly identification, and an end-to-end VLM agent in which visual reasoning directly guides action selection. Across the evaluated models and two paradigms, success rates range from 6.6% to 42.3%, substantially below human performance (83.4%). Through the task of world auditing, WorldAuditBench provides a testbed for studying how multimodal agents couple action and visual reasoning in interactive 3D environments, while highlighting current limitations in their ability to gather and interpret evidence during exploration.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.40325 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T12:14:13.820Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).