Agentic AI for Particle-Based Simulation: Automating SPH Workflows for Debris Flow Modeling

TL;DR

This paper introduces an agentic AI framework for automating meshless particle-based simulations, specifically debris flow modeling with SPH, integrating multimodal inputs and human-in-the-loop interaction to improve automation and user experience.

Contribution

It presents the first agentic AI workflow for meshless simulation in computational mechanics, demonstrating automation of SPH workflows with multimodal inputs and human-in-the-loop capabilities.

Findings

Multimodal inputs improve user experience and reduce failure modes.

Human-in-the-loop is essential for resolving ambiguities in SPH configurations.

The framework shows strong performance in visualization and data extraction tasks.

Abstract

Physics-based simulation underpins engineering analysis but remains difficult to deploy in practice due to complex setup, parameterization, and interpretation. While Large Language Model-based agentic systems have shown promise in automating engineering computing workflows, they have primarily targeted structured, mesh-based problems. We present the first agentic AI workflow for meshless simulation in computational mechanics, demonstrated on debris flow modeling using Smoothed Particle Hydrodynamics (SPH) with the software DualSPHysics. By integrating tool orchestration, multimodal inputs (text and sketches), and human-in-the-loop interaction, the framework enables end-to-end simulation workflows for a class of problems that are inherently less structured and more challenging to automate. Results show that multimodal inputs not only enhance user experience but also reduces failure modes over text-only descriptions. Human-in-the-loop is critical for resolving ambiguities and handling SPH-specific configurations. We further introduce a cognitive-task-based evaluation of post-processing, showing strong performance in visualization and data extraction, with remaining gaps in higher-level SPH-specific physical reasoning that are amenable to improvement through domain-aware modeling. These results establish the viability of agentic AI for particle-based simulation and underscore its potential to transform the accessibility and efficiency of computational mechanics workflows.