mlsanityData to 7 Oct 2026

Large Language Models as Optimization Controllers: Adaptive Continuation for SIMP Topology Optimization

arXiv 2603.25099 ↗First posted 26 Mar 2026cs.CE cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

We present a framework in which a large language model (LLM) acts as an online adaptive controller for SIMP topology optimization, replacing conventional fixed-schedule continuation with real-time, state-conditioned parameter decisions. At every k-th iteration, the LLM receives a structured observation-current compliance, grayness index, stagnation counter, checkerboard measure, volume fraction, and budget consumption-and outputs numerical values for the penalization exponent p, projection sharpness β, filter radius rmin, and move limit δ via a Direct Numeric Control interface. A hard grayness gate prevents premature binarization, and a meta-optimization loop uses a second LLM pass to tune the agent's call frequency and gate threshold across runs. We benchmark the agent against four baselines-fixed (no-continuation), standard three-field continuation, an expert heuristic, and a schedule-only ablation-on three 2-D problems (cantilever, MBB beam, L-bracket) at 120!×!60 resolution and two 3-D problems (cantilever, MBB beam) at 40!×!20!×!10 resolution, all run for 300 iterations. A standardized 40-iteration sharpening tail is applied from the best valid snapshot so that compliance differences reflect only the exploration phase. The LLM agent achieves the lowest final compliance on every benchmark: -5.7% to -18.1% relative to the fixed baseline, with all solutions fully binary. The schedule-only ablation underperforms the fixed baseline on two of three problems, confirming that the LLM's real-time intervention-not the schedule geometry-drives the gain. Code and reproduction scripts will be released upon publication.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 30 of its 77 references that are in the map. First posted on arXiv 26 Mar 2026.

Builds on

30 of 77 references.

References · 30

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2023GPT-4 Technical Reportcited by 18,132
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  6. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  7. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  8. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  9. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  10. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  11. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  12. 2023Large Language Models as Optimizerscited by 830
18 more
  1. 2016Hyperband: A Novel Bandit-Based Approach to Hyperparameter Optimizationcited by 688
  2. 2018Machine Learning for Combinatorial Optimization: a Methodological Tour d'Horizoncited by 612
  3. 2017Population Based Training of Neural Networkscited by 351
  4. 2024ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolutioncited by 266
  5. 2021Hyperparameter Optimization: Foundations, Algorithms, Best Practices and Open Challengescited by 143
  6. 2023Large Language Models as Evolutionary Optimizerscited by 122
  7. 2024Evolutionary Computation in the Era of Large Language Model: Survey and Roadmapcited by 89
  8. 2022Diffusion Models Beat GANs on Topology Optimizationcited by 79
  9. 2020TopologyGAN: Topology Optimization Using Generative Adversarial Networks Based on Physical Fields Over the Initial Domaincited by 65
  10. 2018Deep learning for determining a near-optimal topological design without any iterationcited by 40
  11. 2017Neural networks for topology optimizationcited by 39
  12. 2022Automated Dynamic Algorithm Configurationcited by 37
  13. 2022On the use of Artificial Neural Networks in Topology Optimisationcited by 35
  14. 2021DACBench: A Benchmark Library for Dynamic Algorithm Configurationcited by 28
  15. 2022Topology Optimization via Machine Learning and Deep Learning: A Reviewcited by 22
  16. 2020Self-Directed Online Machine Learning for Topology Optimizationcited by 10
  17. 2023Large Language and Text-to-3D Models for Engineering Design Optimizationcited by 7
  18. 2020A new generation 99 line Matlab code for compliance Topology Optimization and its extension to 3Dcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026AutoSiMP: Autonomous Topology Optimization from Natural Language via LLM-Driven Problem Configuration and Adaptive Solver Controlcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Are Language Models Up to Sequential Optimization Problems? From Evaluation to a Hegelian-Inspired Enhancement
  2. 2025Topological Structure Learning Should Be A Research Priority for LLM-Based Multi-Agent Systems
  3. 2025Learn to Relax with Large Language Models: Solving Constraint Optimization Problems via Bidirectional Coevolution
  4. 2026SimuAgent: An LLM-Based Simulink Modeling Assistant Enhanced with Reinforcement Learning
  5. 2024Large Language Model-Based Evolutionary Optimizer: Reasoning with elitism
  6. 2026SynAct: A Reasoning-Acting Large Language Model Agent for Adaptive Synthesis Optimization
  7. 2026OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving
  8. 2025A Systematic Survey on Large Language Models for Evolutionary Optimization: From Modeling to Solving