Automating structural reliability analysis with a multi-agent large language model framework
Computational Engineering, Finance, and ScienceSoftware Engineering
Summary
The authors developed a system using multiple AI agents to automate reliability analysis for building and infrastructure safety. Their system takes natural-language problem descriptions and produces estimates of how likely components are to fail, involving humans only at key steps for confirmation. Instead of relying solely on AI to generate results, they use trusted computational solvers to ensure accurate and reproducible answers. This approach helps make specialized reliability analysis easier without losing reliability in the results.
Authors
Jaehwan Jeon, Chang Hee Lee, Taeyong Kim
Abstract
Structural reliability analysis supports the design and safety assessment of buildings and civil infrastructure but requires specialized expertise throughout the workflow. This study presents a multi-agent large language model framework that automates component-level reliability analysis from a natural-language problem statement to interpreted estimates of the reliability index and failure probability. Specialized agents handle problem formulation, method planning, code generation, execution, and result interpretation, with human confirmation at key decision points. The Method Planner is fine-tuned using QLoRA for a priori reliability-method category selection. Analysis results are not generated directly by an LLM; instead, validated deterministic solvers compute the reliability estimates, improving reproducibility and reducing hallucination risk. The framework uses open-weight models and supports local execution without closed APIs. Results show that it lowers the expertise barrier to structural reliability assessment while preserving computational trustworthiness.