The Code Behind the Layout: AI Agents for Analog Layout Generators

The paper investigates the role of AI agents in analog layout generation, comparing direct layout drawing by large language models (LLMs) with using generator frameworks like gLayout. Experiments on SKY130 show that drawing layouts directly is costly in time and tokens, whereas building on a generator framework offers reusability and efficient verification across layout families. The authors propose that models should edit generator code and test changes on likely-failing family members, using the results to train local models that generalize edits at lower inference cost.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• llms
• agents