Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Shaoliang Yang, Jun Wang, Yunsheng Wang

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.

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

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 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 pass rate, while the deterministic schedule achieves pass rate at only 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.

Paper Structure

This paper contains 67 sections, 9 equations, 9 figures, 7 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. The Configuration Barrier in Topology Optimization
  3. Beyond Solver Control: The Full Autonomy Gap
  4. The AutoSiMP Approach
  5. Contributions
  6. Related Work
  7. SIMP Topology Optimization
  8. Machine Learning for Topology Optimization
  9. LLM-Driven Automation of Engineering Simulation
  10. Structural analysis from natural language.
  11. End-to-end FEA pipelines.
  12. Shape and design optimization.
  13. Positioning of AutoSiMP.
  14. LLM Agents as Optimizers and Controllers
  15. Method
  16. ...and 52 more sections

Figures (9)

  • Figure 1: AutoSiMP end-to-end autonomous pipeline. A natural-language prompt enters the LLM configurator (Module 1), which produces a validated ProblemSpec. The BC generator (Module 2) converts this into solver-ready arrays. The SIMP solver (Module 3) runs with a pluggable controller. The evaluator (Module 4) checks eight quality metrics. On failure, the retry loop (Module 5) adjusts parameters and re-solves (max 2 retries). The solver is consistent with Yang2026LLMController.
  • Figure 2: LLM Configurator detail (Module 1). A natural-language prompt (left) is processed by Gemini Flash Lite with structured JSON output mode and domain-knowledge interpretation rules (centre). The output is a validated ProblemSpec JSON (right) specifying geometry, mesh, supports, loads, and volume fraction. Deterministic safety rails clamp ranges, detect missing constraints, and validate physical consistency before the specification reaches the solver.
  • Figure 3: Structural quality evaluator (Module 4). The first five checks are pass/fail gates — any failure triggers a retry with adjusted parameters. Checks 6--8 are informational quality metrics reported for analysis but do not block the pipeline. Core gates (blue) ensure structural validity; informational metrics (grey) characterise design quality.
  • Figure 4: Interactive web demo for AutoSiMP. The interface implements the complete five-module pipeline in a browser, supporting both client-side JavaScript solving (instant 2-D) and Python backend solving (production-quality 2-D/3-D with three-field SIMP and 40-iteration sharpening tail). No installation is required beyond a web browser; the Python backend is optional and consists of a single Flask file. None of the systems in Table \ref{['tab:related']} provides an interactive visual interface for topology optimization from natural language.
  • Figure 5: Configuration accuracy (\ref{['tab:pipeline']}): ground-truth (GT) vs. LLM-configured topologies, both solved with the schedule controller at 300 iterations. The first three pairs are visually identical (0.0--0.6% penalty). The simply supported beam shows minor differences (+7.7%). The L-bracket is the one genuine outlier (+119%): the configurator placed the load at a different y-coordinate, producing a structurally different topology.
  • ...and 4 more figures