Interactive Paper Explorer · EPANET + SWMM agentic modelling

EPANET-SWMM-Agentic-Paper-Explorer

A set of interactive explainers for the 2026 agentic water-modelling papers: EPANET-Agentic (Wang, Fu & Savic) and Agentic SWMM (Zhang & Valeo), with a live Agent Lab on Net3, a SWMM5 adaptation, and the ICM-Agent parallel work.

Jian Wang · Guangtao Fu · Dragan Savic — Water Research 293 (2026) 125433 · CC BY open access

Zhonghao Zhang · Caterina Valeo · AI for Engineering 1(1):5 (2026) · doi 10.3390/aieng1010005 · CC BY open access

The problem

Water distribution networks need many model runs for planning and management, but traditional modelling demands complex workflows and specialized expertise. EPANET is the most widely adopted tool for network hydraulics and water-quality simulation, yet its operational complexity restricts accessibility and slows timely decision-making.

The idea

EPANET-Agentic replaces conventional EPANET interfaces and ad-hoc scripts with a natural-language control layer. An engineer types a task in plain English; an LLM orchestrator plans it, delegates to specialised agents that run the EPANET/WNTR code, and interprets the results. The system targets practitioners — system operators, field technicians, and practising engineers doing routine analyses. A human-in-the-loop step approves every agent invocation.

The paper's four highlights:
  • Autonomous, natural-language-driven control of WDN simulations.
  • A multi-agent system: one orchestrator plus three specialised agents.
  • Accurate control and full task completion across diverse hydraulic tasks.
  • Scalable, interpretable, automation-ready WDN management.

At a glance

Engine / library
EPANET via the WNTR Python library
Pattern
Orchestrator + 3 nested tool-agents
LLMs used
DeepSeek-V3, DeepSeek-R1, Qwen-VL-Max
Oversight
Human approval per invocation
Benchmarks
L-Town, C-Town, Net3
Tasks tested
39 (across 4 categories)
Headline result
100% success & tool accuracy, 0 interventions