Papers
arxiv:2606.07850

PDE-Agents: An LLM-Orchestrated Multi-Agent Framework for Automated Finite Element Simulations with Knowledge Graph-Augmented Reasoning

Published on Jun 5
Authors:
,
,

Abstract

A multi-agent system using large language models and GraphRAG knowledge bases automates partial differential equation simulations with improved accuracy and reliability through structured agent coordination and adaptive retrieval strategies.

We present PDE-Agents, a multi-agent ecosystem that automates the full lifecycle of partial differential equation (PDE) / finite element method (FEM) simulations through natural-language interaction. Three specialist large language model (LLM) agents (Simulation, Analytics, Database) are orchestrated via a LangGraph supervisor, with a local open-source LLM stack (Qwen3-Coder-Next, Llama 4 Scout) on dual NVIDIA RTX PRO 6000 GPUs. The architecture is model-agnostic, validated across two LLM generations. A GraphRAG knowledge base (Neo4j, 768-d vector embeddings) encodes curated material properties, known failure patterns, and prior run lineage. We report seven contributions: (i) a verification and validation (V&V) study confirming second-order spatial convergence (O(h^2)) on the heat-equation solver; (ii) a three-way ablation over 50 tasks with a frozen KG (KG On, KG Off, KG Smart), where KG Smart reaches 100% success and the highest output quality (physics 0.933 vs. 0.853 for KG Off; MPF 0.926 vs. 0.796); (iii) a novel-material experiment with three fictional materials known only to the KG, where KG Smart attains near-perfect material property fidelity (MPF = 1.00) versus 0.34 for the KG-free baseline; (iv) a failure analysis tracing KG On's three failures to budget exhaustion and timeout, establishing warm-start injection as the dominant reliability factor; (v) an adaptive framework selecting the optimal retrieval mode per task; (vi) production metrics from 1,369 runs (97.8% success, 57.6% first-try); and (vii) a 100-task KG growth experiment showing a difficulty-dependent gain, with hard-task MPF improving 8.8% while easy/novel tasks stay at ceiling. All code, models, and evaluation artifacts are released openly. Our findings show that integration pattern, not knowledge content, determines whether GraphRAG augmentation helps or hinders LLM agents.

Community

Sign up or log in to comment

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2606.07850 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2606.07850 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2606.07850 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.