An LLM acting as real-time controller for SIMP topology optimization parameters outperforms fixed schedules and heuristics, delivering 5.7-18.1% lower compliance on 2D and 3D benchmarks.
On the trajectories of penalization methods for topol- ogy optimization.Structural and Multidisciplinary Optimization, 21(2):128–139
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CE 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Checkerboarding under SIMP with linear elements localizes to multiaxial load-transfer regions as a discrete stiff substitute for penalized continuous intermediate densities, while uniaxial regions remain free of the pattern.
citing papers explorer
-
Large Language Models as Optimization Controllers: Adaptive Continuation for SIMP Topology Optimization
An LLM acting as real-time controller for SIMP topology optimization parameters outperforms fixed schedules and heuristics, delivering 5.7-18.1% lower compliance on 2D and 3D benchmarks.
-
On the Localization of Checkerboarding in Multiaxial Stress Regions under SIMP Penalization
Checkerboarding under SIMP with linear elements localizes to multiaxial load-transfer regions as a discrete stiff substitute for penalized continuous intermediate densities, while uniaxial regions remain free of the pattern.