Making waves: A conceptual framework exploring how large language model-based multi-agent systems could reshape water engineering

Seyed Hossein Hosseini; Babak Zolghadr-Asli; Henrikki Tenkanen; Kaveh Madani; Mir A. Matin; Ibrahim Demir; Avi Ostfeld; Vijay P. Singh; Dragan Savic

doi:10.1016/j.watres.2025.125157

Back

Making waves: A conceptual framework exploring how large language model-based multi-agent systems could reshape water engineering

Journal article

Open access

Peer reviewed

Making waves: A conceptual framework exploring how large language model-based multi-agent systems could reshape water engineering

Seyed Hossein Hosseini, Babak Zolghadr-Asli, Henrikki Tenkanen, Kaveh Madani, Mir A. Matin, Ibrahim Demir, Avi Ostfeld, Vijay P. Singh and Dragan Savic

Water research (Oxford), Vol.291, 125157

12/12/2025

DOI: 10.1016/j.watres.2025.125157

PMID: 41448011

Files and links (1)

url

https://doi.org/10.1016/j.watres.2025.125157View

Published (Version of record) Open Access

Abstract

•LLM-MA systems can enhance water engineering by improving data integration, monitoring, and decision-making.•Specialized agents can support groundwater monitoring, irrigation scheduling, reservoir management, and post-disaster response.•Key challenges include data access, computational demands, bias, hallucinations, and governance issues. Large Language Model-based Multi-Agents (LLM-MAs) are emerging systems that manage complex tasks with specialized and coordinated agents. In this paper, we present new perspectives on the integration of LLM-MA systems into enhancing water engineering practices. Water engineering typically involves data integration, analysis, modelling, decision-making, and cross-disciplinary collaboration, which often present significant difficulties. To address these domain-specific complexities, we explore how LLM-MA systems can support advanced operations in water engineering and facilitate them. 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. [Display omitted]

Adaptive AI systems

Decision support systems

Generative AI

Large language model-based multi-agent (LLM-MA)

Water engineering

Details

Title: Subtitle: Making waves: A conceptual framework exploring how large language model-based multi-agent systems could reshape water engineering
Creators: Seyed Hossein Hosseini - Aalto University
Babak Zolghadr-Asli - University of Exeter
Henrikki Tenkanen - Aalto University
Kaveh Madani - United Nations University Institute for Water, Environment, and Health
Mir A. Matin - United Nations University Institute for Water, Environment, and Health
Ibrahim Demir - University of New Orleans
Avi Ostfeld - Technion – Israel Institute of Technology
Vijay P. Singh - Texas A&M University
Dragan Savic - University of Exeter
Resource Type: Journal article
Publication Details: Water research (Oxford), Vol.291, 125157
DOI: 10.1016/j.watres.2025.125157
PMID: 41448011
NLM abbreviation: Water Res
ISSN: 0043-1354
eISSN: 1879-2448
Publisher: Elsevier Ltd; OXFORD
Language: English
Date published: 12/12/2025
Academic Unit: Electrical and Computer Engineering; Civil and Environmental Engineering; Injury Prevention Research Center
Record Identifier: 9985096039202771

Metrics

4 Record Views