A constrained LLM front-end for FEniCS multi-physics simulations dispatches to human-written templates and achieves 100% valid parses plus 90-100% geometry success on benchmarks while avoiding LLM-generated solver code.
Integrating large language models for automated structural analysis
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
A multi-agent LLM system using 2D grid projection and specialized agents for nodes, girders, columns, and loads generates executable scripts for 3D frame analysis, achieving 90% accuracy on ten test cases.
A two-stage multi-agent LLM converts structural inputs to JSON then platform-specific scripts for ETABS, SAP2000, and OpenSees, achieving over 90% accuracy on 20 frame problems across ten trials.
IterSIMP-σ integrates multimodal LLMs for proposing spatial density interventions in stress-aware SIMP topology optimization, yielding comparable but statistically non-significant performance gains over rule-based baselines on 2D and 3D benchmarks.
Literature on system prompts for AI shows fragmented and contradictory claims that complicate policy efforts to use them as reliable governance mechanisms.
citing papers explorer
-
A Constrained Natural-Language Interface for Variational Multi-Physics Finite Element Simulations in FEniCS
A constrained LLM front-end for FEniCS multi-physics simulations dispatches to human-written templates and achieves 100% valid parses plus 90-100% geometry success on benchmarks while avoiding LLM-generated solver code.
-
Agentic Large Language Models for Automated Structural Analysis of 3D Frame Systems
A multi-agent LLM system using 2D grid projection and specialized agents for nodes, girders, columns, and loads generates executable scripts for 3D frame analysis, achieving 90% accuracy on ten test cases.
-
Automating Structural Analysis Across Multiple Software Platforms Using Large Language Models
A two-stage multi-agent LLM converts structural inputs to JSON then platform-specific scripts for ETABS, SAP2000, and OpenSees, achieving over 90% accuracy on 20 frame problems across ten trials.
-
IterSIMP-{\sigma}: Evaluating LLM-Assisted Spatial Interventions in Stress-Aware Topology Optimization
IterSIMP-σ integrates multimodal LLMs for proposing spatial density interventions in stress-aware SIMP topology optimization, yielding comparable but statistically non-significant performance gains over rule-based baselines on 2D and 3D benchmarks.
-
Prompt Governance? On Governing Technologies Governed by Natural Language
Literature on system prompts for AI shows fragmented and contradictory claims that complicate policy efforts to use them as reliable governance mechanisms.