AI RESEARCH
From Perception to Autonomous Computational Modeling: A Multi-Agent Approach
arXiv CS.CL
•
ArXi:2604.06788v1 Announce Type: cross 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.