MOOSEnger -- a Domain-Specific AI Agent for the MOOSE Ecosystem

TL;DR

MOOSEnger is an AI agent that simplifies setting up and debugging complex MOOSE simulations by translating natural language into executable inputs, significantly improving success rates over baseline methods.

Contribution

It introduces a domain-specific AI tool that combines retrieval-augmented generation with deterministic parsing and validation for MOOSE simulations, enhancing usability and reliability.

Findings

Achieves 0.90 success rate on benchmark prompts

Outperforms LLM-only baseline with 0.06 success rate

Provides integrated validation and execution feedback

Abstract

MOOSEnger is a tool-enabled AI agent tailored to the Multiphysics Object-Oriented Simulation Environment (MOOSE). MOOSE cases are specified in HIT ".i" input files; the large object catalog and strict syntax make initial setup and debugging slow. MOOSEnger offers a conversational workflow that turns natural-language intent into runnable inputs by combining retrieval-augmented generation over curated docs/examples with deterministic, MOOSE-aware parsing, validation, and execution tools. A core-plus-domain architecture separates reusable agent infrastructure (configuration, registries, tool dispatch, retrieval services, persistence, and evaluation) from a MOOSE plugin that adds HIT-based parsing, syntax-preserving ingestion of input files, and domain-specific utilities for input repair and checking. An input precheck pipeline removes hidden formatting artifacts, fixes malformed HIT structure with a bounded grammar-constrained loop, and resolves invalid object types via similarity search over an application syntax registry. Inputs are then validated and optionally smoke-tested with the MOOSE runtime in the loop via an MCP-backed execution backend (with local fallback), translating solver diagnostics into iterative verify-and-correct updates. Built-in evaluation reports RAG metrics (faithfulness, relevancy, context precision/recall) and end-to-end success by actual execution. On a 125-prompt benchmark spanning diffusion, transient heat conduction, solid mechanics, porous flow, incompressible Navier--Stokes, phase field and plasticity, MOOSEnger achieves a 0.90 execution pass rate versus 0.06 for an LLM-only baseline.