Agentic AI for Particle-Based Simulation: Automating SPH Workflows for Debris Flow Modeling
For computational mechanics practitioners, this work demonstrates the feasibility of automating particle-based simulation workflows, which are less structured than mesh-based ones, though the approach is domain-specific and incremental.
This paper presents the first agentic AI workflow for meshless simulation, automating debris flow modeling using SPH (DualSPHysics). Multimodal inputs reduce failure modes over text-only, and human-in-the-loop is critical for SPH-specific configurations, with strong performance in visualization and data extraction.
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.