Metraipolis › archive › dc_7a0e1fa84da8
VehicleArena: A Realistic Urban Environment for Multi-Agent Driving — arXiv:2609.35916
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.35916
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T16:21:11.632Z
- SHA-256 of the archived text
ce43fca82521eb1b4299f5235cd44eeabd5672f97ff402e2448b2ce21cc7c82b- Stable URL of this page
https://metraipolis.com/documento/dc_7a0e1fa84da8
How to cite
VehicleArena: A Realistic Urban Environment for Multi-Agent Driving — arXiv:2609.35916 — arXiv (en), https://arxiv.org/abs/2609.35916 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7a0e1fa84da8 (Metraipolis archive dc_7a0e1fa84da8, sha256 ce43fca82521eb1b4299f5235cd44eeabd5672f97ff402e2448b2ce21cc7c82b)
BibTeX
@misc{dc7a0e1fa84da8,
title = {VehicleArena: A Realistic Urban Environment for Multi-Agent Driving — arXiv:2609.35916},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.35916},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7a0e1fa84da8; sha256 ce43fca82521eb1b4299f5235cd44eeabd5672f97ff402e2448b2ce21cc7c82b},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35916. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Real-world embodied agents often pursue independent objectives within a shared physical environment, where their actions can alter the conditions faced by others. Existing benchmarks, however, typically assume shared goals or explicitly prescribed interaction protocols, leaving such emergent physical coupling underexplored. We introduce VehicleArena, a 3D urban-driving benchmark for studying independently operating agents in a dynamic shared world. In VehicleArena, LLM-controlled agents must fulfill evolving passenger requests while navigating complex traffic, and each agent's driving decisions can reshape traffic flow, delays, risks, and subsequent observations for surrounding agents. The benchmark provides 112 evaluation tasks spanning single-agent and multi-agent driving. Across nine evaluated models, the highest arrival rates reach only 65.0% on single-agent tasks and 65.6% on multi-agent tasks, while strong passenger-request or cabin scores do not reliably translate into successful trip completion. Moreover, in matched multi-agent runs, every tested focal policy reduces the arrival rate of surrounding vehicles relative to the simulator's native traffic controller, revealing measurable externalities beyond the focal vehicle itself. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.MA). Categorie arXiv: Multiagent Systems (cs.MA) ; Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.35916 — 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 2026-10-07T15:54:11.789Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).