Metraipolis › archive › dc_e85209979458

RT-Safe: Benchmarking Agent Safety in Real-Time Embodied Environment — arXiv:2610.09294

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09294
License (as archived)
CC0-1.0
Archived
2026-10-08T11:09:11.186Z
SHA-256 of the archived text
f99f01616d9a1651c1138f7d5f4ea05702984c23b6b71fcd30442fbde9030b4d
Stable URL of this page
https://metraipolis.com/documento/dc_e85209979458

How to cite

RT-Safe: Benchmarking Agent Safety in Real-Time Embodied Environment — arXiv:2610.09294 — arXiv (en), https://arxiv.org/abs/2610.09294 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e85209979458 (Metraipolis archive dc_e85209979458, sha256 f99f01616d9a1651c1138f7d5f4ea05702984c23b6b71fcd30442fbde9030b4d)
BibTeX
@misc{dce85209979458,
  title = {RT-Safe: Benchmarking Agent Safety in Real-Time Embodied Environment — arXiv:2610.09294},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09294},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e85209979458; sha256 f99f01616d9a1651c1138f7d5f4ea05702984c23b6b71fcd30442fbde9030b4d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09294. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Rapid progress in AI agents has brought growing attention to agent safety, with extensive evaluation focused on digital environments. As agents move into the physical world, embodied safety becomes increasingly important: failures can cause human injury and costly hardware damage. Beyond selecting safe actions, embodied agents must also operate under real-time constraints: the physical world does not pause while an agent reasons. As pedestrians move and vehicles approach during inference, an action that appears safe at observation time may become unsafe before execution. Real-time embodied safety therefore depends on both decision quality and decision latency. We introduce RT-SAFE, a simulated urban benchmark for evaluating embodied-agent safety under real-time constraints. RT-SAFE combines navigation tasks with moving actors, environmental hazards, and traffic rules, while allowing the world to evolve throughout inference and action execution. Across eight VLMs, agents achieve high task completion yet almost never complete safely: in the hardest setting, only 0.7% of episodes finish without a safety event. More strikingly, matched static and real-time evaluations yield task completion rates of 91.3% and 94.1%, respectively, while real-time execution increases collisions by $12.3\times$. These results reveal that standard task success can mask substantial safety failures, and that decision latency itself can become a source of physical risk. Finally, we show that RT-SAFE can support offline RL training and substantially reduce collision rates while achieving strong task completion.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.09294 — 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 2026-10-08T10:14:05.924Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).