EGU26-18353, updated on 14 Mar 2026
https://doi.org/10.5194/egusphere-egu26-18353
EGU General Assembly 2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Oral | Wednesday, 06 May, 16:30–16:40 (CEST)
 
Room 2.15
Large Language Model-Based Multi-Agent Systems: The Next Frontier in Digital Water Engineering 
Seyed Hossein Hosseini1, Babak Zolghadr-Asli2,3, Henrikki Tenkanen4, Kaveh Madani5, Mir A. Matin6, Ibrahim Demir7,8, Avi Ostfeld9, Vijay P. Singh10, and Dragan Savic11,12
Seyed Hossein Hosseini et al.
  • 1Department of Built Environment, School of Engineering, Aalto University, Espoo, Finland (seyed.h.hosseini@aalto.fi)
  • 2Centre for Water Systems, University of Exeter, Exeter, UK
  • 3Sustainable Minerals Institute, The University of Queensland, Brisbane, Australia (b.zolghadrasli@uq.net.au)
  • 4Department of Built Environment, School of Engineering, Aalto University, Espoo, Finland (henrikki.tenkanen@aalto.fi)
  • 5United Nations University Institute for Water, Environment and Health (UNU-INWEH), Richmond Hill, ON, Canada (kaveh.madani@unu.edu)
  • 6United Nations University Institute for Water, Environment and Health (UNU-INWEH), Richmond Hill, ON, Canada (mir.matin@unu.edu)
  • 7River-Coastal Science and Engineering, Tulane University, New Orleans, LA, 70118, USA
  • 8ByWater Institute, Tulane University, New Orleans, LA, 70118, USA (idemir@tulane.edu)
  • 9Faculty of Civil and Environmental Engineering, Technion- Israel Institute of Technology, Israel (ostfeld@technion.ac.il)
  • 10Department of Biological and Agricultural Engineering and Zachry Department of Civil and Environmental Engineering, Texas A&M University, 6848 Truxton Drive, Dallas, Texas 756231, USA (vijay.singh@ag.tamu.edu)
  • 11Centre for Water Systems, University of Exeter, Exeter, EX4 4QF, United Kingdom
  • 12KWR Water Research Institute, Niuwegein, 3430 BB, the Netherlands (d.savic@exeter.ac.uk)
Large Language Model-based Multi-Agents (LLM-MAs) are emerging systems that manage complex tasks with specialized and coordinated agents. Water engineering typically involves data integration, analysis, modeling, decision-making, and cross-disciplinary collaboration, which often present significant difficulties. To address these domain-specific complexities, we explore and present new perspectives on how LLM-MA systems can support and enhance advanced operations in water engineering. By pointing out the linguistic capabilities of LLMs and the modular, scalable, and collaborative architecture of LLM-MA systems, we investigate the role of intelligent agents in enabling timely, adaptive, and traceable solutions. Various practical applications were identified, e.g., LLM-MA for pressure drop detection in water distribution networks, flood management, or in their role as potential negotiating agents to find a balanced solution considering differing goals. Our investigation highlights both the capabilities and limitations of LLM-MAs in water engineering and proposes practical recommendations for their effective implementation within the field. This study seeks to develop a foundational framework for understanding how LLM-MAs can shape the future of water engineering processes.
 
Reference: Hosseini, Seyed Hossein, Babak Zolghadr-Asli, Henrikki Tenkanen, Kaveh Madani, Mir A. Matin, Ibrahim Demir, Avi Ostfeld, Vijay P. Singh, and Dragan Savic. "Making waves: A conceptual framework exploring how large language model-based multi-agent systems could reshape water engineering." Water Research (2025): 125157.

How to cite: Hosseini, S. H., Zolghadr-Asli, B., Tenkanen, H., Madani, K., Matin, M. A., Demir, I., Ostfeld, A., Singh, V. P., and Savic, D.: Large Language Model-Based Multi-Agent Systems: The Next Frontier in Digital Water Engineering , EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-18353, https://doi.org/10.5194/egusphere-egu26-18353, 2026.