Metraipolis › archive › dc_cfff78ccc98c

UrbanAgent: A Tool-Augmented Agent for Cross-System Urban Tasks — arXiv:2608.03018

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.03018
License (as archived)
CC0-1.0
Archived
2026-10-31T12:15:30.581Z
SHA-256 of the archived text
952685159aee09b61c53a6953f1520dadf378b9593eeeeabe00aebdf7db38fe8
Stable URL of this page
https://metraipolis.com/documento/dc_cfff78ccc98c

How to cite

UrbanAgent: A Tool-Augmented Agent for Cross-System Urban Tasks — arXiv:2608.03018 — arXiv (en), https://arxiv.org/abs/2608.03018 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cfff78ccc98c (Metraipolis archive dc_cfff78ccc98c, sha256 952685159aee09b61c53a6953f1520dadf378b9593eeeeabe00aebdf7db38fe8)
BibTeX
@misc{dccfff78ccc98c,
  title = {UrbanAgent: A Tool-Augmented Agent for Cross-System Urban Tasks — arXiv:2608.03018},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.03018},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cfff78ccc98c; sha256 952685159aee09b61c53a6953f1520dadf378b9593eeeeabe00aebdf7db38fe8},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03018. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Modern cities rely on an increasing number of digital services to operate, but residents' daily needs are still difficult to meet. Services are fragmented and have little interoperability, placing a heavy operational burden on users. Existing digital platforms, urban foundation models, and intelligent assistants each address only isolated aspects of an urban task. But they struggle to reliably convert complex natural-language requests into executable cross-system workflows. We propose Urban-Agent, a tool-augmented agent framework for cross-system urban tasks. It couples the cognitive and reasoning capabilities of a large language model with a tool-set supporting code execution, API calls, and Model Context Protocol. Through one adaptive closed loop, it clarifies missing information before acting, grounds tool use in live observations, and aligns the final response with observed evidence and task constraints. To address the evaluation gap, we introduce Urban-Eval, a benchmark specifically designed for cross-system urban request. Unlike prior benchmarks that assess either general tool use or urban knowledge and reasoning, Urban-Eval evaluates both task results and execution quality, including required tool coverage, dependency validity, and evidence traceability. Experimental results indicate that Urban-Agent reaches a 71% task success rate, 10 points above the strongest baseline. This lead holds across GPT-5-mini, Gemini-2.5-flash, DeepSeek-V4-flash, and Qwen3-235B-A22B.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.03018 — 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 2026-10-31T12:05:52.741Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).