IterSIMP-σ: Evaluating LLM-Assisted Spatial Interventions in Stress-Aware Topology Optimization
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918510242824192 |
|---|---|
| author | Yang, Shaoliang Wang, Jun Wang, Yunsheng |
| author_facet | Yang, Shaoliang Wang, Jun Wang, Yunsheng |
| contents | This paper studies whether multimodal large language models (LLMs) can serve as inspectable spatial proposal modules for stress-aware topology optimization. IterSIMP-σ keeps the SIMP optimizer as a compliance-minimizing finite-element solver and places a deterministic stress pass, gate evaluator, and hybrid LLM/rule interpreter around it. After each solve, density and von Mises stress fields are rendered; the interpreter proposes ranked spatial interventions; and deterministic safeguards accept, reject, or stop each action. The main action is a soft density seed, where selected elements are initialized at elevated density before the next solve but remain free under the optimality-criteria update. We evaluate the loop on a 16-problem 2D controller-policy benchmark, a six-problem exploratory 3D extension, passive-solid and input ablations, stress-threshold sensitivity, and a fixed-volume attribution study comparing LLM proposals with deterministic max-stress hotspot seeding, random stress-region seeding, and rule-based control. The 2D controller-policy benchmark shows a small retained-compliance difference (1.9% lower geometric mean for the soft-seed LLM), but this diagnostic is not statistically significant (W = 33, two-sided p = 0.382) and is not a fixed-volume feasible-final comparison. In the fixed-volume study, the LLM condition completed 44/48 attempted evaluations; 25/44 completed evaluations produced all-gate-passing retained states. Feasible-final scoring against rule-based control is split 4/4/1, and deterministic exact-hotspot seeding remains competitive. Accepted LLM spatial actions with per-step records have mean normalized seed-to-hotspot distance 0.221. The results support IterSIMP-σ as an inspectable LLM-assisted design-automation framework for spatial interventions, not yet as evidence that LLM visual reasoning improves stress-constrained optimization. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_19110 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | IterSIMP-σ: Evaluating LLM-Assisted Spatial Interventions in Stress-Aware Topology Optimization Yang, Shaoliang Wang, Jun Wang, Yunsheng Computational Engineering, Finance, and Science This paper studies whether multimodal large language models (LLMs) can serve as inspectable spatial proposal modules for stress-aware topology optimization. IterSIMP-σ keeps the SIMP optimizer as a compliance-minimizing finite-element solver and places a deterministic stress pass, gate evaluator, and hybrid LLM/rule interpreter around it. After each solve, density and von Mises stress fields are rendered; the interpreter proposes ranked spatial interventions; and deterministic safeguards accept, reject, or stop each action. The main action is a soft density seed, where selected elements are initialized at elevated density before the next solve but remain free under the optimality-criteria update. We evaluate the loop on a 16-problem 2D controller-policy benchmark, a six-problem exploratory 3D extension, passive-solid and input ablations, stress-threshold sensitivity, and a fixed-volume attribution study comparing LLM proposals with deterministic max-stress hotspot seeding, random stress-region seeding, and rule-based control. The 2D controller-policy benchmark shows a small retained-compliance difference (1.9% lower geometric mean for the soft-seed LLM), but this diagnostic is not statistically significant (W = 33, two-sided p = 0.382) and is not a fixed-volume feasible-final comparison. In the fixed-volume study, the LLM condition completed 44/48 attempted evaluations; 25/44 completed evaluations produced all-gate-passing retained states. Feasible-final scoring against rule-based control is split 4/4/1, and deterministic exact-hotspot seeding remains competitive. Accepted LLM spatial actions with per-step records have mean normalized seed-to-hotspot distance 0.221. The results support IterSIMP-σ as an inspectable LLM-assisted design-automation framework for spatial interventions, not yet as evidence that LLM visual reasoning improves stress-constrained optimization. |
| title | IterSIMP-σ: Evaluating LLM-Assisted Spatial Interventions in Stress-Aware Topology Optimization |
| topic | Computational Engineering, Finance, and Science |
| url | https://arxiv.org/abs/2605.19110 |