LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation

Chen-Chia Chang, Wan-Hsuan Lin, Yikang Shen, Yiran Chen, Xin Zhang
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:7351-7360, 2025.

Abstract

Automation of analog topology design is crucial due to customized requirements of modern applications with heavily manual engineering efforts. The state-of-the-art work applies a sequence-to-sequence approach and supervised finetuning on language models to generate topologies given user specifications. However, its circuit formulation is inefficient due to $O(|V|^2)$ token length and suffers from low precision sensitivity to numeric inputs. In this work, we introduce LaMAGIC2, a succinct float-input canonical formulation with identifier (SFCI) for language model-based analog topology generation. SFCI addresses these challenges by improving component-type recognition through identifier-based representations, reducing token length complexity to $O(|V|)$, and enhancing numeric precision sensitivity for better performance under tight tolerances. Our experiments demonstrate that LaMAGIC2 achieves 34% higher success rates under a tight tolerance 0.01 and 10X lower MSEs compared to a prior method. LaMAGIC2 also exhibits better transferability for circuits with more vertices with up to 58.5% improvement. These advancements establish LaMAGIC2 as a robust framework for analog topology generation.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-chang25b, title = {{L}a{MAGIC}2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation}, author = {Chang, Chen-Chia and Lin, Wan-Hsuan and Shen, Yikang and Chen, Yiran and Zhang, Xin}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {7351--7360}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/chang25b/chang25b.pdf}, url = {https://proceedings.mlr.press/v267/chang25b.html}, abstract = {Automation of analog topology design is crucial due to customized requirements of modern applications with heavily manual engineering efforts. The state-of-the-art work applies a sequence-to-sequence approach and supervised finetuning on language models to generate topologies given user specifications. However, its circuit formulation is inefficient due to $O(|V|^2)$ token length and suffers from low precision sensitivity to numeric inputs. In this work, we introduce LaMAGIC2, a succinct float-input canonical formulation with identifier (SFCI) for language model-based analog topology generation. SFCI addresses these challenges by improving component-type recognition through identifier-based representations, reducing token length complexity to $O(|V|)$, and enhancing numeric precision sensitivity for better performance under tight tolerances. Our experiments demonstrate that LaMAGIC2 achieves 34% higher success rates under a tight tolerance 0.01 and 10X lower MSEs compared to a prior method. LaMAGIC2 also exhibits better transferability for circuits with more vertices with up to 58.5% improvement. These advancements establish LaMAGIC2 as a robust framework for analog topology generation.} }
Endnote
%0 Conference Paper %T LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation %A Chen-Chia Chang %A Wan-Hsuan Lin %A Yikang Shen %A Yiran Chen %A Xin Zhang %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-chang25b %I PMLR %P 7351--7360 %U https://proceedings.mlr.press/v267/chang25b.html %V 267 %X Automation of analog topology design is crucial due to customized requirements of modern applications with heavily manual engineering efforts. The state-of-the-art work applies a sequence-to-sequence approach and supervised finetuning on language models to generate topologies given user specifications. However, its circuit formulation is inefficient due to $O(|V|^2)$ token length and suffers from low precision sensitivity to numeric inputs. In this work, we introduce LaMAGIC2, a succinct float-input canonical formulation with identifier (SFCI) for language model-based analog topology generation. SFCI addresses these challenges by improving component-type recognition through identifier-based representations, reducing token length complexity to $O(|V|)$, and enhancing numeric precision sensitivity for better performance under tight tolerances. Our experiments demonstrate that LaMAGIC2 achieves 34% higher success rates under a tight tolerance 0.01 and 10X lower MSEs compared to a prior method. LaMAGIC2 also exhibits better transferability for circuits with more vertices with up to 58.5% improvement. These advancements establish LaMAGIC2 as a robust framework for analog topology generation.
APA
Chang, C., Lin, W., Shen, Y., Chen, Y. & Zhang, X.. (2025). LaMAGIC2: Advanced Circuit Formulations for Language Model-Based Analog Topology Generation. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:7351-7360 Available from https://proceedings.mlr.press/v267/chang25b.html.

Related Material