AutoSiMP: Autonomous Topology Optimization from Natural Language via LLM-Driven Problem Configuration and Adaptive Solver Control

2026-03-27

AI Summary

This work proposes the first fully automated framework for optimizing binary structural topologies that are both compliant with natural language specifications and validated to pass rigorous quality checks. The method leverages a large language model (LLM) to interpret user requirements and automatically generate optimization parameters, integrating a three-field SIMP solver, Heaviside projection, plug-in continuity control, and eight structural quality verification mechanisms. End-to-end autonomous optimization is achieved through adaptive scheduling and a closed-loop retry strategy. Evaluated on ten diverse benchmark cases, the framework attains 100% configuration accuracy and a median compliance penalty of only +0.3%. With the incorporation of a scheduling controller, all cases pass every quality check on the first attempt, substantially enhancing automation and practical engineering applicability.

Abstract

We present AutoSiMP, an autonomous pipeline that transforms a natural-language structural problem description into a validated, binary topology without manual configuration. The pipeline comprises five modules: (1) an LLM-based configurator that parses a plain-English prompt into a validated specification of geometry, supports, loads, passive regions, and mesh parameters; (2) a boundary-condition generator producing solver-ready DOF arrays, force vectors, and passive-element masks; (3) a three-field SIMP solver with Heaviside projection and pluggable continuation control; (4) an eight-check structural evaluator (connectivity, compliance, grayness, volume fraction, convergence, plus three informational quality metrics); and (5) a closed-loop retry mechanism. We evaluate on three axes. Configuration accuracy: across 10 diverse problems the configurator produces valid specifications on all cases with a median compliance penalty of $+0.3\%$ versus expert ground truth. Controller comparison: on 17 benchmarks with six controllers sharing an identical sharpening tail, the LLM controller achieves the lowest median compliance but $76.5\%$ pass rate, while the deterministic schedule achieves $100\%$ pass rate at only $+1.5\%$ higher compliance. End-to-end reliability: with the schedule controller, all LLM-configured problems pass every quality check on the first attempt $-$ no retries needed. Among the systems surveyed in this work (Table 1), AutoSiMP is the first to close the full loop from natural-language problem description to validated structural topology. The complete codebase, all specifications, and an interactive web demo will be released upon journal acceptance.

Problem

• topology optimization
• natural language
• autonomous system
• structural design
• LLM-driven

Innovation

• topology optimization
• large language model (LLM)
• autonomous design
• SIMP
• natural language interface