Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces a multi-agent framework leveraging LLMs to automate computational mechanics workflows, from processing perceptual data of engineering components to generating actionable engineering reports. The framework uses LLM agents as conditioned operators on a shared context space, incorporating quality gates for conditional iteration and mathematical formalisms for uncertainty quantification. A demonstration on a steel L-bracket photograph resulted in a complete finite element analysis pipeline, including mesh generation, multiple analyses, and a code-compliant assessment, all autonomously executed.
LLM agents can now autonomously execute complex computational mechanics workflows directly from perceptual data, but don't fire your engineers just yet: human review remains critical.
We present a solver-agnostic framework in which coordinated large language model (LLM) agents autonomously execute the complete computational mechanics workflow, from perceptual data of an engineering component through geometry extraction, material inference, discretisation, solver execution, uncertainty quantification, and code-compliant assessment, to an engineering report with actionable recommendations. Agents are formalised as conditioned operators on a shared context space with quality gates that introduce conditional iteration between pipeline layers. We introduce a mathematical framework for extracting engineering information from perceptual data under uncertainty using interval bounds, probability densities, and fuzzy membership functions, and introduce task-dependent conservatism to resolve the ambiguity of what `conservative'means when different limit states are governed by opposing parameter trends. The framework is demonstrated through a finite element analysis pipeline applied to a photograph of a steel L-bracket, producing a 171,504-node tetrahedral mesh, seven analyses across three boundary condition hypotheses, and a code-compliant assessment revealing structural failure with a quantified redesign. All results are presented as generated in the first autonomous iteration without manual correction, reinforcing that a professional engineer must review and sign off on any such analysis.