TopoSizing: An LLM-aided Framework of Topology-based Understanding and Sizing for AMS Circuits
This addresses the problem of inefficient and opaque automated design flows for analog and mixed-signal circuits, representing an incremental improvement by integrating existing methods like graph algorithms and LLMs into a novel framework.
The authors tackled the challenge of analog and mixed-signal circuit design by proposing TopoSizing, an end-to-end framework that uses graph algorithms and LLM agents for circuit understanding and optimization, achieving improved efficiency in Bayesian optimization while preserving feasibility.
Analog and mixed-signal circuit design remains challenging due to the shortage of high-quality data and the difficulty of embedding domain knowledge into automated flows. Traditional black-box optimization achieves sampling efficiency but lacks circuit understanding, which often causes evaluations to be wasted in low-value regions of the design space. In contrast, learning-based methods embed structural knowledge but are case-specific and costly to retrain. Recent attempts with large language models show potential, yet they often rely on manual intervention, limiting generality and transparency. We propose TopoSizing, an end-to-end framework that performs robust circuit understanding directly from raw netlists and translates this knowledge into optimization gains. Our approach first applies graph algorithms to organize circuits into a hierarchical device-module-stage representation. LLM agents then execute an iterative hypothesis-verification-refinement loop with built-in consistency checks, producing explicit annotations. Verified insights are integrated into Bayesian optimization through LLM-guided initial sampling and stagnation-triggered trust-region updates, improving efficiency while preserving feasibility.