EUVIMEDEUVIMED entdecken
Crossref

RESPOND: Realistic Environment Simulation of Population and Natural Disasters with LLM-Driven Agents (Student Abstract)

Roman Sultimov, Mikhail Mozikov, Dmitrii Abramov, Mariia Kovalchuk, Maksim Malykh, Aleksandr Volkov, Ilya Makarov, Andrei Osiptsov, Yury Maximov

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41396-41397

DOI: 10.1609/aaai.v40i48.42283 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Roman Sultimov und 8 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Climate change is driving more frequent and severe disasters, putting people and infrastructure at risk. Protecting communities requires models that capture both natural disasters dynamics and how people behave under extreme conditions. This demo presents RESPOND, a multi-agent LLM-enhanced platform that jointly simulates natural hazards and human response. RESPOND couples high-fidelity flood AI forecasting an agent-based model of human behavior. LLM modules improve each agent decision-making, enabling context-aware reasoning over alerts, road closures, social signals, and changing water levels. The system simulates evacuation flows, resource seeking, and communication patterns producing actionable outputs for emergency management, urban planning, and policy. In the live demo one can run what-if or predicted scenarios, adjust assumptions, and observe emergent population behavior and risk hot spots in real time. By tightly coupling dynamic hazards with LLM-driven multi-agent behavior, RESPOND moves beyond fragmented tools and offers a practical, integrated platform for disaster preparedness and response.

Zitieren

APA

Sultimov, R., Mozikov, M., Abramov, D., Kovalchuk, M., Malykh, M., Volkov, A., Makarov, I., Osiptsov, A., & Maximov, Y. (2026). RESPOND: Realistic Environment Simulation of Population and Natural Disasters with LLM-Driven Agents (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41396-41397. https://doi.org/10.1609/aaai.v40i48.42283

Vancouver

Sultimov R, Mozikov M, Abramov D, Kovalchuk M, Malykh M, Volkov A, et al. RESPOND: Realistic Environment Simulation of Population and Natural Disasters with LLM-Driven Agents (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41396-41397. doi:10.1609/aaai.v40i48.42283

BibTeX
@article{Sultimov2026,
  author = {Sultimov, Roman and Mozikov, Mikhail and Abramov, Dmitrii and Kovalchuk, Mariia and Malykh, Maksim and Volkov, Aleksandr and Makarov, Ilya and Osiptsov, Andrei and Maximov, Yury},
  title = {RESPOND: Realistic Environment Simulation of Population and Natural Disasters with LLM-Driven Agents (Student Abstract)},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {48},
  pages = {41396--41397},
  doi = {10.1609/aaai.v40i48.42283}
}
Kostenlos starten →