Automating SWMM-based stormwater modelling and analysis through a tool-augmented single-agent system.

Evaluation on the Astlingen benchmark included capability demonstrations and a 60-task suite comprising 20 static, 20 dynamic, and 20 scenario-based tasks, executed once with each of three LLMs to produce 180 model-task runs.

Across 180 runs, 89 of 100 failed tool calls were followed by a successful corrective call within three attempts.

SWMM-Agentic also reproduced network characteristics, compared alternative control strategies, and conducted a human-framed rain-garden experiment that showed decreasing combined sewer overflow discharge with diminishing marginal benefits at higher coverage.