Towards Expert-Level Analog Layout Design: Large Language Model as Optimizer

Analog physical design requires coordinated decisions about device placement, routing, and the parasitics that determine circuit performance. Yet much of its automation optimizes individual stages, leaving engineers to reconcile downstream electrical failures with earlier layout choices. We introduce LAMBDA, a large language model based analog physical design framework that combines global reasoning with fast automated execution. To connect reasoning with execution, a customized B${}^{\ast }$ Graph unifies analog constraints, placement, and routing in an executable search space, enabling a multimodal LLM to optimize coupled design decisions using circuit knowledge, layout observations, and accumulated experience. Multi-fidelity optimization couples low-cost physical and parasitic models with detailed electrical evaluation feedback, balancing exploration efficiency with post-layout performance. On nine commercial 28-nm circuits, LAMBDA improves geometric mean full layout area and wirelength and the composite analog electrical score over SOTA baselines.